Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 46
Encontrada(s) 1 página(s)

RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Adapted generative latent diffusion models for accurate pathological analysis in chest X-ray images

  • Iglesias Morís, Daniel
  • Moura, Joaquim de
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
Funding for open access charge: Universidade da Coruña/CISUG, [Absctract]: Respiratory diseases have a significant global impact, and assessing these conditions is crucial for improving patient outcomes. Chest X-ray is widely used for diagnosis, but expert evaluation can be challenging. Automatic computer-aided diagnosis methods can provide support for clinicians in these tasks. Deep learning has emerged as a set of algorithms with exceptional potential in such tasks. However, these algorithms require a vast amount of data, often scarce in medical imaging domains. In this work, a new data augmentation methodology based on adapted generative latent diffusion models is proposed to improve the performance of an automatic pathological screening in two high-impact scenarios: tuberculosis and lung nodules. The methodology is evaluated using three publicly available datasets, representative of real-world settings. An ablation study obtained the highest-performing image generation model configuration regarding the number of training steps. The results demonstrate that the novel set of generated images can improve the performance of the screening of these two highly relevant pathologies, obtaining an accuracy of 97.09%, 92.14% in each dataset of tuberculosis screening, respectively, and 82.19% in lung nodules. The proposal notably improves on previous image generation methods for data augmentation, highlighting the importance of the contribution in these critical public health challenges., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This work was supported by Ministerio de Ciencia e Innovación, Government of Spain through the research project with [grant numbers PID2019-108435RB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educación, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [grant number ED431C 2020/24], predoctoral grant [grant number ED481A 2021/196]; CITIC, Centro de Investigación de Galicia [grant number ED431G 2019/01], receives financial support from Consellería de Educación, Universidade e Formación Profesional, Xunta de Galicia, through the ERDF (80%) and Secretaría Xeral de Universidades (20%). Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED481A 2021/196
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Intra- and Inter-expert Validation of an Automatic Segmentation Method for Fluid Regions Associated with Central Serous Chorioretinopathy in OCT Images

  • Gende, M.
  • Castelo Martínez, Lúa
  • Moura, Joaquim de
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
[Absctract]: Central Serous Chorioretinopathy (CSC) is a retinal disorder caused by the accumulation of fluid, resulting in vision distortion. The diagnosis of this disease is typically performed through Optical Coherence Tomography (OCT) imaging, which displays any fluid buildup between the retinal layers. Currently, these fluid regions are manually detected by visual inspection a time-consuming and subjective process that can be prone to errors. A series of six deep learning-based automatic segmentation architectural configurations of different levels of complexity were trained and compared in order to determine the best model intended for the automatic segmentation of CSC-related lesions in OCT images. The best performing models were then evaluated in an external validation study. Furthermore, an intra- and inter-expert analysis was conducted in order to compare the manual segmentation performed by expert ophthalmologists with the automatic segmentation provided by the models. Test results of the best performing configuration achieved a mean Dice of in the internal dataset. In the external validation set, these models achieved a level of agreement with human experts of up to 0.960 in terms of Kappa coefficient, contrasting with a value of 0.951 for agreement between human experts. Overall, the models reached a better agreement with either of the human experts than these experts with each other, suggesting that automatic segmentation models for the detection of CSC-related lesions in OCT imaging can be useful tools for assessing this disease, reducing the workload of manual inspection and leading to a more robust and objective diagnosis method., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This research was funded by Instituto de Salud Carlos III, Government of Spain (research project DTS18/00136); Ministerio de Ciencia e Innovación, Government of Spain (research projects PID2019-108435RB-I00, TED2021-131201B-I00, PDC2022-133132-I00); Consellería de Cultura, Educación e Universidade, Xunta de Galicia, through Grupos de Referencia Competitiva (grant number ED431C 2020/24) and predoctoral grant (grant number ED481A 2021/161); and CITIC, Centro de Investigación de Galicia (grant number ED431G 2019/01), and receives financial support from Consellería de Educación, Universidade e Formación Profesional, Xunta de Galicia, through the ERDF (80%) and Secretaría Xeral de Universidades (20%). The funding sources had no role in the development of this work., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED481A 2021/161, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Sistema automático para a segmentación das capas da retina en pacientes con glaucoma mediante OCT

  • Gende, M.
  • Moura, Joaquim de
  • Robles, Patricia
  • Fernández-Vigo, José Ignacio
  • Martínez-de-la-Casa, José María
  • García-Feijóo, Julián
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
BIOINTEGRASAÚDE 2023, celebrada en A Coruña o día 14 de Decembro de 2023, organizada polo Instituto de Investigación Biomédica da Coruña (INIBIC), o Instituto de Investigación Sanitaria de Santiago de Compostela (IDIS) e o Instituto de Investigación Sanitaria Galicia Sur (IISGS), É fundamental realizar unha diagnose precoz do glaucoma para preservar a saúde visual dos pacientes. Mediante distintos patróns de Tomografía de Coherencia Óptica (OCT), é posible medir o grosor das capas do tecido nervioso en diferentes partes da retina, extraendo información sobre o seu estado e a súa evolución. Neste traballo, presentamos dúas aproximacións automáticas baseadas en aprendizaxe profunda para a segmentación das capas da retina nos tres patróns OCT máis comúns para a diagnose do glaucoma: escaneos circulares ao redor do disco óptico, radiais a través do disco óptico, e volumétricos extraídos sobre a superficie macular. A primeira aproximación aproveita a similitude entre as distintas vistas da retina para adestrar un único modelo multi-vista capaz de realizar a segmentación en calquera dos patróns. A segunda aproximación utiliza unha serie de modelos especificamente adestrados para maximizar a precisión en cada unha das vistas, precedido por unha fase de decisión na que se determina automaticamente o modelo axeitado para analizar cada imaxe. Obtivéronse resultados satisfactorios, cunha precisión de 0.85±0.07 e 0.88±0.09, así coma unha exhaustividade de 0.87±0.06 e 0.87±0.07, respectivamente, para a primeira e segunda aproximación. O uso destes sistemas pode resultar de gran utilidade á hora de acadar unha diagnose precoz desta patoloxía, axudando a preservar a calidade de vida dos pacientes., Este traballo foi financiado polo Ministerio de Ciencia e Innovación y Universidades, Gobierno de España (refs. PID2019-108435RB-I00, TED2021-131201B-I00, e PDC2022-133132-I00); Consellería de Cultura, Educación e Universidade, Xunta de Galicia a través de grupos de referencia competitiva con ref. ED431C 2020/24 e da axuda predoutoral con ref. ED481A 2021/161.
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Domain-specific multi-transfer approaches for deep learning-based glaucoma screening in high myopia patients

  • Goyanes, Elena
  • Moura, Joaquim de
  • Lelong, Antoine
  • Robles, Patricia
  • Martínez-de-la-Casa, José María
  • Moreno-Montañes, Javier
  • Muñoz-Negrete, Francisco J.
  • Rodríguez-Uña, Ignacio
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
[Abstract]: Glaucoma is a leading cause of irreversible blindness worldwide, with early detection being essential to preventing vision loss. However, diagnosing glaucoma in highly myopic patients poses significant challenges due to anatomical alterations, such as optic nerve head deformation and retinal nerve fiber layer thinning, potentially obscuring key disease features and causing misdiagnosis. To address these limitations, we propose a novel deep learning-based framework for automated glaucoma screening in highly myopic eyes. Our approach leverages multi-transfer learning, integrating large-scale pretraining with domain-specific adaptation using ophthalmic disease datasets. This methodology enables the model to extract robust and highly discriminative features, improving sensitivity to glaucomatous changes in myopic eyes. Additionally, we incorporate domain transfer pipeline to address the distributional differences between standard datasets and myopia-specific cases, further enhancing the model’s generalization capabilities. To rigorously evaluate our approach, we conduct a comprehensive analysis of state-of-the-art architectures and transfer learning strategies, assessing their impact on classification performance. Experimental results demonstrate that the proposed model consistently outperforms baseline methods, achieving superior accuracy and robustness in glaucoma detection within highly myopic populations. These findings underscore the potential of AI-driven screening tools as reliable and accurate diagnostic aids, supporting clinicians in the early detection and effective management of glaucoma in complex cases., This work was supported by Ministerio de Ciencia e Innovación, Government of Spain through the research project with [grant numbers PID2023-148913OB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educación, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [grant number ED431C 2024/33], predoctoral grant [grant number ED481A-2023-152]. Also supported by the ISCIII under the grant [FORT23/00010], and research project [PI23/00828]: Desarrollo evaluación de un algoritmo de detección de glaucoma a partir de un abordaje multimodal en pacientes con miopía magna, as well as The Research Grant 2022-2024 as part of the Programa FORTALECE of Ministerio de Ciencia e Innovación and CNPq/MCTI/FNDCT [grant Number: 444625/2024-0]. Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431C 2024/33, Xunta de Galicia; ED481A-2023-152, Brasil. Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq); 444625/2024-0, Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Automatic Deep Learning-based Models for Retinal Layer Thickness Analysis as a Biomarker for Neurodegenerative Diseases

  • Gende, M.
  • Moura, Joaquim de
  • Cordón Ciordia, Beatriz
  • Viladés, Elisa
  • García-Martín, Elena
  • Sánchez, Clara I.
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
The ARVO Annual Meeting is the premiere gathering for eye and vision scientists at all career stages, students, and those in affiliated fields to share the latest research findings and collaborate on innovative solutions. For 2023, the Meeting will be hosted April 23 – 27 in New Orleans, La., Purpose : The retina is the most accessible part of the central nervous system, allowing its non-invasive exploration and measurement. Optical Coherence Tomography (OCT) offers an objective monitoring method of progression in Neurodegenerative Disease (NDD), enabling the extraction of biomarkers such as retinal layer thickness. Machine learning models allow the automatic and repeatable measurement of the retinal layers and enable an early diagnosis of NDD. These need to be trained on annotated images representative of the visual patterns that characterise these diseases. We present a study in the automatic measurement of retinal layer thickness in patients of different NDDs and an assessment of the mutual compatibility of models trained in representative images of these diseases. Methods : Five independent samples of multiple sclerosis, Alzheimer's disease, Parkinson's disease and essential tremor patients, along with healthy controls were prospectively recruited (N=50). Macula centred OCT volumes from these patients were annotated with the area of the Retinal Nerve Fibre Layer (RNFL) and between the Ganglion Cell Layer and Bruch's Membrane (GCL-BM), for 1250 B-scans in total. In a first experiment, a series of deep learning models were trained on every NDD but one and evaluated in terms of their ability to segment the retinal layers of the unseen NDD. In a second experiment, the models were trained on images from a specific NDD and then evaluated on each of the other ones. Results : The average thickness for each layer was measured and separately compared for each NDD using a one-way ANOVA test. This test found no significant differences between the thickness of either RNFL or GCL-BM (p>0.05). The results show that the models are able to accurately segment the retinal layers, with an overall Dice coefficient of 0.96±0.02 for Experiment 1 and 0.95±0.03 for Experiment 2. However, these results do not translate equally for every NDD. The models trained in diseases such as Alzheimer's and essential tremor can better generalise to other NDDs, while healthy control images achieved the second worst results. Conclusions : Patients of different NDDs may present visual differences in their retinal OCTs, which affect the performance of automatic retinal layer segmentation models., This research was funded by Instituto de Salud Carlos III, Government of Spain, [research projects PI17/01726 and PI20/00437]; Inflammatory Disease Network (RICORS) [research project RD21/0002/0050]; Ministerio de Ciencia e Innovación, Government of Spain [research projects RTI2018-095894-B-I00, PID2019-108435RB-I00 and TED2021-131201B-I00]; Consellería de Cultura, Educación e Universidade, Xunta de Galicia, through Grupos de Referencia Competitiva [grant number ED431C 2020/24], predoctoral grant [grant number ED481A 2021/161]; CITIC, Centro de Investigación de Galicia [grant number ED431G 2019/01], receives financial support from Consellería de Educación, Universidade e Formación Profesional, Xunta de Galicia, through the ERDF (80%) and Secretaría Xeral de Universidades (20%). The funding organisations had no role in the design or conduct of this research., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED481A 2021/161, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Multi-Stage Learning for Intuitive Visualization of Microcystic Macular Edema in OCT Images

  • Vidal, Plácido
  • Moura, Joaquim de
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
Ethical Approval: This study was performed in line with the principles of the Declaration of Helsinki. Approval was granted by the Ethics Committee of Investigation from A Coruña/Ferrol (24th of november, 2014/No. 2014/437). All OCT images used in this paper were obtained under explicit informed consent by the subjects., Code Availability: The source code for the experiments conducted in this research is available at the following GitHub repository: https://github.com/PlacidoFranciscoLizancosVidal/Microcysts_paper_code., [Abstract]: Purpose; Detecting and monitoring Microcystic Macular Edema (MME) in Optical Coherence Tomography (OCT) images is vital for early diagnosis of Diabetic Macular Edema (DME), a leading cause of blindness in developed countries. However, detecting MME remains challenging due to its fuzzy boundaries and diffuse nature. In this work, we propose a novel fully-automatic methodology based on multi-stage regional learning to successfully detect and visualize MME in OCT images. Methods: Our work is divided into two main stages: the first stage coarsely identifies general DME accumulations in the innermost retinal layers. On the other hand, the second stage precisely detects MME within the reduced search space. These detections are then used to generate intuitive confidence maps. Results: Our approach achieves a mean confidence of 0.9618 ± 0.0518 per MME pixel, demonstrating consistent and strong detections. This robust methodology facilitates early diagnosis of MME, independent of clinicians’ subjectivity, and has the potential to significantly impact the quality of life of patients. Conclusion: Our work represents a significant advancement in the automatic analysis of complex retinal pathologies. Source code is available at: https://github.com/PlacidoFranciscoLizancosVidal/Microcysts_paper_code., This work was supported by Ministerio de Ciencia e Innovación, Government of Spain through the research project with [Grant Nos. PID2023-148913OB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educación, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [Grant No. ED431C 2024/33]. Also supported by the ISCIII under the Grant [FORT23/00010] as part of the Programa FORTALECE of Ministerio de Ciencia e Innovación. Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature., Xunta de Galicia; ED431C 2024/33
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Visualization of pathological changes in retinal layer thickness using optical coherence tomography

  • López-Varela, Emilio
  • Barreira, Noelia
  • Olivier Pascual, Nuria
  • Quezada-Sánchez, Johnny
  • Oreja-Guevara, Celia
[Abstract]: Optical Coherence Tomography (OCT) is a non-invasive imaging technique that provides high-resolution cross-sectional images of biological tissues. Biomarkers such as the thickness of retinal layers can be used for the evaluation of several diseases such as glaucoma or multiple sclerosis. In this work, we create the thickness profiles of healthy and pathological eyes using a statistical model and developed a methodology to compare the thickness profiles of OCT images with the models and visually inspect the abnormal areas. This approach allows for a quick assessment of the retinal layers health, assisting clinicians and easing the diagnostic burden., This research was funded by Government of Spain, Ministerio de Ciencia e Innovación y Universidades, Government of Spain, RTI2018-095894-B-I00 research project; Ministerio de Ciencia e Innovación, Government of Spain through the research projects with reference PID2019-108435RB-I00, reference PDC2022-133132-I00 and TED2021-131201B-I00; Consellería de Cultura, Educación e Universidade, Xunta de Galicia through the Grupos de Referencia Competitiva, grant ref. ED431C 2020/24; Emilio López Varela acknowledges its support under FPI PID2019-108435RB-I00 project., Xunta de Galicia; ED431C 2020/24
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Phytoplankton detection and recognition in freshwater digital microscopy images using deep learning object detectors

  • Figueroa, Jorge
  • Rivas-Villar, David
  • Rouco, José
  • Novo Buján, Jorge
[Absctract]: Water quality can be negatively affected by the presence of some toxic phytoplankton species, whose toxins are difficult to remove by conventional purification systems. This creates the need for periodic analyses, which are nowadays manually performed by experts. These labor-intensive processes are affected by subjectivity and expertise, causing unreliability. Some automatic systems have been proposed to address these limitations. However, most of them are based on classical image processing pipelines with not easily scalable designs. In this context, deep learning techniques are more adequate for the detection and recognition of phytoplankton specimens in multi-specimen microscopy images, as they integrate both tasks in a single end-to-end trainable module that is able to automatize the adaption to such a complex domain. In this work, we explore the use of two different object detectors: Faster R-CNN and RetinaNet, from the one-stage and two-stage paradigms respectively. We use a dataset composed of multi-specimen microscopy images captured using a systematic protocol. This allows the use of widely available optical microscopes, also avoiding manual adjustments on a per-specimen basis, which would require expert knowledge. We have made our dataset publicly available to improve the reproducibility and to foment the development of new alternatives in the field. The selected Faster R-CNN methodology reaches maximum recall levels of 95.35%, 84.69%, and 79.81%, and precisions of 94.68%, 89.30% and 82.61%, for W. naegeliana, A. spiroides, and D. sociale, respectively. The system is able to adapt to the dataset problems and improves the results overall with respect to the reference state-of-the-art work. In addition, the proposed system improves the automation and abstraction from the domain and simplifies the workflow and adjustment., This research was funded by Ministerio de Innovación, Government of Spain [research projects PDC2022-133132-I00, PID2019-108435RB-I00 and TED2021-131201B-I00]; Consellería de Cultura, Educación e Universidade, Xunta de Galicia through the predoctoral grant contracts ref. ED481A 2021/147 and ED481A 2023/059, and Grupos de Referencia Competitiva, grant ref. ED431C 2020/24; CITIC, Centro de Investigación de Galicia ref. ED431G 2019/01, receives financial support from Consellería de Educación, Universidade e Formación Profesional, Xunta de Galicia, through the ERDF (80%) and Secretaría Xeral de Universidades (20%)., Xunta de Galicia; ED481A 2021/147, Xunta de Galicia; ED481A 2023/059, Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Automatic identification of neurodegenerative diseases with 3D point cloud-based analysis using geometric deep learning in OCT retinal images

  • Álvarez-Rodríguez, Lorena
  • Pueyo-Bestué, Ana
  • Moura, Joaquim de
  • García Prego, Iván
  • Viladés, Elisa
  • García-Martín, Elena
  • Sánchez, Clara I.
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
[Abstract]: Neurodegenerative diseases (NDDs) such as Alzheimer’s (AD), Multiple Sclerosis (MS), and Parkinson’s (PD) are becoming increasingly prevalent, requiring reliable biomarkers for early detection and monitoring. Retinal layers, as captured by Optical Coherence Tomography (OCT), offer a promising avenue for automated analysis via deep learning methods. This study explores the use of Geometric Deep Learning (GDL) techniques, which redefine input data, for these prevalent and clinically significant diseases screening using point clouds extracted from Retinal Nerve Fibre Layer (RNFL) and Ganglion Cell Layer (GCL-BM) contours. Three representative GDL architectures were applied to three different analyses: (I) differentiating all NDDs from a control group, (II) separating each NDD from the control group, and (III) performing multi-class classification among the diseases. Optimal point cloud sizes were also investigated. Results showed that in analysis (I), the GDL strategy achieved a high F1-score of 0.92 using only 512 3D points. In analysis (II), with 1,024, 4,096, and 1,024 3D points, it achieved F1-scores of 0.93, 0.94, and 0.97 for AD, MS, and PD, respectively. In analysis (III), multi-class screening reached a F1-score of 0.87. These results demonstrate the effectiveness of using subsampled point clouds for differentiating NDDs and suggest that GDL methods can enhance the efficiency of retinal layer analysis, offering improvements over current state-of-the-art techniques. This highlights the potential of GDL in processing retinal data and advancing NDD detection and classification, with top-performing results obtained using only around 8% of the total 3D points from a sample., This work was supported by the Instituto de Salud Carlos III, Spain (ISCIII), Government of Spain [grant numbers PI17/01726, PI20/00437, PI23/00935, RD21/0002/0050 (Inflammatory Disease Network - RICORS), FORT23/00010 (Programa FORTALECE)], the Ministerio de Ciencia e Innovación, Spain, Government of Spain [grant numbers PID2023-148913OB-I00, TED2021-131201B-I00, and PDC2022-133132-I00], the Consellería de Educación, Universidade, e Formación Profesional, Xunta de Galicia, Spain, Grupos de Referencia Competitiva [grant number ED431C 2024/33] and by the Government of Aragon [group B23 23R]. This work was also supported by the Horizon Europe Programme through the ACHILLES/101189689 project (HORIZON-CL4-2024-DATA-01-01). Also supported by the CNPq/MCTI/FNDCT [grant Number: 444625/2024-0]. Funding for open access charge: Universidade da Coruña/CISUG., Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Multi-task localization of the hemidiaphragms and lung segmentation in portable chest X-ray images of COVID-19 patients

  • Iglesias Morís, Daniel
  • Moura, Joaquim de
  • Aslani, Shahab
  • Jacob, Joseph
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
[Absctract]: Background: The COVID-19 can cause long-term symptoms in the patients after they overcome the disease. Given that this disease mainly damages the respiratory system, these symptoms are often related with breathing problems that can be caused by an affected diaphragm. The diaphragmatic function can be assessed with imaging modalities like computerized tomography or chest X-ray. However, this process must be performed by expert clinicians with manual visual inspection. Moreover, during the pandemic, the clinicians were asked to prioritize the use of portable devices, preventing the risk of cross-contamination. Nevertheless, the captures of these devices are of a lower quality. Objectives: The automatic quantification of the diaphragmatic function can determine the damage of COVID-19 on each patient and assess their evolution during the recovery period, a task that could also be complemented with the lung segmentation. Methods: We propose a novel multi-task fully automatic methodology to simultaneously localize the position of the hemidiaphragms and to segment the lung boundaries with a convolutional architecture using portable chest X-ray images of COVID-19 patients. For that aim, the hemidiaphragms’ landmarks are located adapting the paradigm of heatmap regression. Results: The methodology is exhaustively validated with four analyses, achieving an 82.31% +- 2.78% of accuracy when localizing the hemidiaphragms’ landmarks and a Dice score of 0.9688 +- 0.0012 in lung segmentation. Conclusions: The results demonstrate that the model is able to perform both tasks simultaneously, being a helpful tool for clinicians despite the lower quality of the portable chest X-ray images., The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by Ministerio de Ciencia e Innovación, Government of Spain through the research project with [grant numbers PID2019-108435RB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educación, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [grant number ED431C 2020/24], predoctoral grant [grant number ED481A 2021/196]; CITIC, Centro de Investigación de Galicia [grant number ED431G 2019/01], receives financial support from Consellería de Educación, Universidade e Formación Profesional, Xunta de Galicia, through the ERDF (80%) and Secretaría Xeral de Universidades (20%). This research was funded in whole or in part by the Wellcome Trust [209553/Z/17/Z]. For the purpose of open access, the author has applied a CC-BY public copyright licence to any author accepted manuscript version arising from this submission., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED431G 2019/01, Xunta de Galicia; ED481A 2021/196, Wellcome Trust; 209553/Z/17/Z
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Análisis de datos multimodales para la toma de decisiones clínicas utilizando Inteligencia Artificial en el contexto de la COVID-19

  • Iglesias Morís, Daniel
  • Moura, Joaquim de
  • Marcos, Pedro J.
  • Míguez-Rey, Enrique
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
BIOINTEGRASAÚDE 2023, celebrada en A Coruña o día 14 de Decembro de 2023, organizada polo Instituto de Investigación Biomédica da Coruña (INIBIC), o Instituto de Investigación Sanitaria de Santiago de Compostela (IDIS) e o Instituto de Investigación Sanitaria Galicia Sur (IISGS), [Abstract]: La COVID-19 es una enfermedad pulmonar infecciosa causante de la pandemia mundial del año 2020. En los momentos críticos de las emergencias sanitarias, el equipo médico debe tomar decisiones importantes en un contexto de recursos limitados. En este contexto, los métodos de diagnóstico asistido por ordenador pueden ayudar en esa toma de decisiones, permitiendo identificar a los pacientes de alto riesgo. Esto se puede realizar utilizando información extraída de historiales clínicos electrónicos, tests de laboratorio o estudios de imagen. En este trabajo, presentamos un nuevo método eficiente y totalmente automático para estimar el riesgo de pacientes COVID-19, utilizando la fusión de datos multimodales con características clínicas y características profundas extraídas a partir de imágenes de radiografía torácica. Esta estimación se efectúa en 2 escenarios críticos: riesgo de hospitalización y riesgo de fallecimiento. Los resultados demuestran un gran desempeño por parte de los clasificadores, estimando ambos riesgos con una gran precisión y utilizando únicamente un subconjunto muy reducido de un conjunto de características originales notablemente más extenso. Esta reducción de la dimensionalidad en el conjunto de datos es muy ventajosa en escenarios donde los recursos computacionales son limitados. Este método totalmente automático presenta un potencial prometedor para mejorar el proceso de toma de decisiones clínicas y una mejor gestión de los recursos médicos, no solo en el contexto de la COVID-19 sino también en otros escenarios clínicos., Este trabajo está financiado por el Ministerio de Ciencia e Innovación, Gobierno de España por medio del proyecto de investigación con los códigos [RTI2018-095894-B-I00, PID2019-108435RB-I00, TED2021-131201B-I00 y PDC2022-133132-I00]; Consellería de Educación, Universidade e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [código ED431C 2020/24], ayuda predoctoral [código ED481A 2021/196]., Xunta de Galicia; ED481A 2021/196, Xunta de Galicia; ED431C 2020/24
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Efficient clinical decision-making process via AI-based multimodal data fusion: A COVID-19 case study

  • Iglesias Morís, Daniel
  • Moura, Joaquim de
  • Marcos, Pedro J.
  • Míguez-Rey, Enrique
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
[Abstract]: COVID-19 is an infectious disease that caused a global pandemic in 2020. In the critical moments of this healthcare emergencies, the medical staff needs to take important decisions in a context of limited resources that must be carefully managed. To this end, the computer-aided diagnosis methods are extremely powerful and help them to better recognize the evidences of high-risk patients. This can be done with the support of relevant information extracted from electronic health records, lab tests and imaging studies. In this work, we present a novel fully-automatic efficient method to help the clinical decision-making process in the context of COVID-19 risk estimation, using multimodal data fusion of clinical features and deep features extracted from chest X-ray images. The risk estimation is studied in two of the most relevant and critical encountered scenarios: the risk of hospitalization and mortality. This study shows which are the most important features for each scenario, the ratio of clinical and imaging features present in the top ranking and the performance of the used machine learning models. The results demonstrate a great performance by the classifiers, estimating the risk of hospitalization with an AUC-ROC of 0.8452 ± 0.0133 and the risk of death with an AUC-ROC of 0.8285 ± 0.0210, only using a subset of the original features, and highlight the significant contribution of imaging features to hospitalization risk assessment, while clinical features become more crucial for mortality risk evaluation. Furthermore, multimodal data fusion can outperform the approaches that use one data source. Despite the model’s complexity, it requires fewer features, an advantage in scenarios with limited computational resources. This streamlined, fully-automated method shows promising potential to improve the clinical decision-making process and better manage medical resources, not only in the context of COVID-19, but also in other clinical scenarios., This work was supported by Ministerio de Ciencia e Innovación, Government of Spain through the research project with [grant numbers PID2023-148913OB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educación, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [grant number ED431C 2024/33], predoctoral grant [grant number ED481A 2021/196]. Also supported by the ISCIII under the grant [FORT23/00010] as part of the Programa FORTALECE of Ministerio de Ciencia e Innovación., Xunta de Galicia; ED431C 2024/33, Xunta de Galicia; ED481A 2021/196
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

ConKeD: multiview contrastive descriptor learning for keypoint-based retinal image registration

  • Rivas-Villar, David
  • Hervella, Álvaro S.
  • Rouco, José
  • Novo Buján, Jorge
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: Retinal image registration is of utmost importance due to its wide applications in medical practice. In this context, we propose ConKeD, a novel deep learning approach to learn descriptors for retinal image registration. In contrast to current registration methods, our approach employs a novel multi-positive multi-negative contrastive learning strategy that enables the utilization of additional information from the available training samples. This makes it possible to learn high-quality descriptors from limited training data. To train and evaluate ConKeD, we combine these descriptors with domain-specific keypoints, particularly blood vessel bifurcations and crossovers, that are detected using a deep neural network. Our experimental results demonstrate the benefits of the novel multi-positive multi-negative strategy, as it outperforms the widely used triplet loss technique (single-positive and single-negative) as well as the single-positive multi-negative alternative. Additionally, the combination of ConKeD with the domain-specific keypoints produces comparable results to the state-of-the-art methods for retinal image registration, while offering important advantages such as avoiding pre-processing, utilizing fewer training samples, and requiring fewer detected keypoints, among others. Therefore, ConKeD shows a promising potential towards facilitating the development and application of deep learning-based methods for retinal image registration., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This work is supported by Ministerio de Ciencia e Innovación, Government of Spain, through the PID2019-108435RB-I00, TED2021-131201B-I00, and PDC2022-133132-I00 research projects; Consellería de Cultura, Educación e Universidade, Xunta de Galicia, through Grupos de Referencia Competitiva ref. ED431C 2020/24, predoctoral fellowship ref. ED481A 2021/147 and the postdoctoral fellowship ref. ED481B-2022-025; and Instituto de Salud Carlos III (ISCIII) under the grant FORT23/00010 as part of the Programa FORTALECE of Ministerio de Ciencia e Innovación. Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED481A 2021/147, Xunta de Galicia; ED481B-2022-025
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Fully-automatic end-to-end approaches for 3D drusen segmentation in Optical Coherence Tomography images

  • Goyanes, Elena
  • Leyva Santarén, Saúl
  • Herrero, Paula
  • Moura, Joaquim de
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
Presented at: 28th International Conference on Knowledge Based and Intelligent information and Engineering Systems (KES 2024), [Abstract]: Drusen, small lipid deposits located below the retina, are early biomarkers of age-related macular degeneration (AMD), a condition that leads to visual impairment worldwide, especially among the elderly. The presence of AMD is linked with Alzheimer’s Disease (AD) and dense deposit disease (DDD), emphasizing the critical need for early and accurate detection of drusen in retinal tissues. Optical Coherence Tomography (OCT), with its non-invasive and high-resolution imaging capabilities, stands as a pivotal tool for early AMD diagnosis through the identification of drusen. However, the reliance on manual segmentation of drusen in 3D OCT images introduces significant challenges: it is not only time-consuming but also subject to inter-observer variability, severely constraining its efficacy for widespread screening applications. These limitations underscore the critical need for an automated solution that can improve diagnostic workflows, ensure consistency across interpretations, and facilitate the processing of large datasets with improved accuracy and efficiency. In response, we propose a new deep learning-based, fully-automatic end-to-end approach for the segmentation of drusen in 3D OCT volumes. Complementary, a pivotal aspect of our research involves the first detailed comparative analysis between 2D and 3D end-to-end approaches. This comparison is crucial for understanding the impact of dimensional spatial information on the accuracy of drusen segmentation within OCT scans. The findings demonstrate that the 3D approach, by leveraging the depth and complexity of spatial data available in 3D OCT volumes, markedly surpasses the 2D approach. This superior performance underlines the importance of 3D spatial information in enhancing diagnostic precision. Through automating the segmentation process, our proposal not only makes AMD screening more efficient and precise but also significantly advances the diagnosis of retinal diseases, potentially enriching our understanding of systemic conditions connected through retinal biomarkers., This work was supported by Ministerio de Ciencia e Innovacion, Government of Spain through the research project with [grant numbers PID2019-108435RB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educacion, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [grant number ED431C 2020/24] and predoctoral grant [grant number ED481A-2023-152]. Furthermore, this work was supported by the Instituto de Salud Carlos III (ISCIII) under the grant [FORT23/00010] as part of the Programa FORTALECE del Ministerio de Ciencia e Innovacion., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED481A-2023-152
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Heatmap-guided balanced multi-task learning approach for glistening characterization in OCT images

  • Álvarez-Rodríguez, Lorena
  • Moura, Joaquim de
  • Fernández-Vigo, José Ignacio
  • Macarro-Merino, Ana
  • Fernández-Vigo, José A.
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
©2025 Elsevier B.V. All rights reserved. This manuscript version is made available under the CC-BY-NC-ND 4.0 license https://creativecommons.org/licenses/bync-nd/4.0/. This version of the article has been accepted for publication in Biomedical Signal Processing and Control. The Version of Record is available online at https://doi.org/10.1016/j.bspc.2025.107527, [Abstract]: Glistening in intraocular lenses (IOLs) refers to the formation of water-filled microvacuoles within the lens material, typically assessed via slit-lamp (SL) photography. Recent proposals, like Optical Coherence Tomography (OCT) combined with deep learning, offer promising alternatives for evaluating glistenings. This study proposes a novel, automated multi-task method for detecting glistenings and segmenting the IOL area (IOLa) using heatmap-guided segmentation. Exhaustive experimentation demonstrates the method's generalization and stability across diverse IOL models with varying glistening severity, offering a dataset 375% more variable than previous studies. The study focuses on two tasks: glistening detection (Task I) and IOLa segmentation (Task II). For Task I, two single-task baselines were tested: a classical deep learning approach (a) and heatmap-guided segmentation (b). The best configurations achieved Intraclass Correlation Coefficient (ICC) scores of 0.901 for baseline (a) and 0.946 for baseline (b), while the multi-task approach reached 0.939. In Task II, improvements in segmentation accuracy were less pronounced but still achieved high Dice scores, consistently above 0.910. This research is the first to apply balanced multi-task strategies and heatmap-guided segmentation for glistening detection and to tackle IOLa segmentation. The method's competitive results confirm the value of deep learning for characterizing glistenings in OCT images, utilizing a more diverse and clinically representative dataset. This approach advances the field by providing a more reliable and efficient method for glistening evaluation., This work was supported by Ministerio de Ciencia e Innovación, Government of Spain through the research project with [grant numbers PID2023-148913OB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educación, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, Spain, [grant number ED431C 2024/33]. Also supported by the ISCIII, Spain under the grant [FORT23/00010] as part of the Programa FORTALECE of Ministerio de Ciencia e Innovación., Xunta de Galicia; ED431C 2024/33
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Evolutionary mosaicking for high-resolution wide-field optical coherence tomography angiography

  • Martínez-Río, Javier
  • Carmona, Enrique J.
  • Cancelas, Daniel
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
[Abstract]: Optical coherence tomography angiography (OCTA) is a noninvasive imaging modality that produces retinal blood flow images. However, the limited field of view (FOV) of typical high-resolution scan poses challenges for comprehensive analysis. This work presents a fully automatic method for generating high-resolution wide-field OCTA mosaics from overlapping scans, addressing the need for wider FOVs without requiring advanced OCTA equipment or manual mosaicking. The proposed approach consists of a three-stage pipeline: an initial mosaic is constructed using correlation-based template matching, refined with an evolutionary algorithm to optimize vascular continuity at seams, and finalized with a blending stage to improve overall quality. Unlike existing methods, our approach avoids keypoint extraction or input image preprocessing, making it robust against noise and artifacts typically present in clinical OCTA images. Using a correlation-based metric that measures the degree of vascular continuity at the seams in each mosaic, we obtained a mean and standard deviation equal to (before blending) for all the mosaics analyzed. The proposed method presented robust results, producing high-resolution wide-field OCTA mosaics., This work was supported by the Ministerio de Ciencia, Innovación y Universidades, Government of Spain, through the RTI2018-095894- B-I00, PID2019-108435RB-I00, TED2021-131201B-I00 and PDC2022- 133132-I00 research projects; Consellería de Educación, Universidade e Formación Profesional, Xunta de Galicia, through Grupos de Referencia Competitiva ref. ED431C 2020/24. Two of the authors of this work also receive financial support from the European Social Fund, through the predoctoral contract ref. PEJD-2019-PRE/TIC-17030 and research assistant contract ref. PEJ-2019-AI/TIC-13771., Xunta de Galicia; ED431C 2020/24, Comunidad de Madrid; PEJD-2019-PRE/TIC-17030, Comunidad de Madrid; PEJ-2019-AI/TIC-13771
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Fully automatic segmentation and monitoring of choriocapillaris flow voids in OCTA images

  • López-Varela, Emilio
  • Moura, Joaquim de
  • Novo Buján, Jorge
  • Fernández-Vigo, José Ignacio
  • Moreno-Morillo, Francisco Javier
  • Ortega Hortas, Marcos
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG., [Abstract]: Optical coherence tomography angiography (OCTA) is a non-invasive ophthalmic imaging modality that is widely used in clinical practice. Recent technological advances in OCTA allow imaging of blood flow deeper than the retinal layers, at the level of the choriocapillaris (CC), where a granular image is obtained showing a pattern of bright areas, representing blood flow, and a pattern of small dark regions, called flow voids (FVs). Several clinical studies have reported a close correlation between abnormal FVs distribution and multiple diseases, so quantifying changes in FVs distribution in CC has become an area of interest for many clinicians. However, CC OCTA images present very complex features that make it difficult to correctly compare FVs during the monitoring of a patient. In this work, we propose fully automatic approaches for the segmentation and monitoring of FVs in CC OCTA images. First, a baseline approach, in which a fully automatic segmentation methodology based on local contrast enhancement and global thresholding is proposed to segment FVs and measure changes in their distribution in a straightforward manner. Second, a robust approach in which, prior to the use of our segmentation methodology, an unsupervised trained neural network is used to perform a deformable registration that aligns inconsistencies between images acquired at different time instants. The proposed approaches were tested with CC OCTA images collected during a clinical study on the response to photodynamic therapy in patients affected by chronic central serous chorioretinopathy (CSC), demonstrating their clinical utility. The results showed that both approaches are accurate and robust, surpassing the state of the art, therefore improving the efficacy of FVs as a biomarker to monitor the patient treatments. This gives great potential for the clinical use of our methods, with the possibility of extending their use to other pathologies or treatments associated with this type of imaging., Xunta de Galicia; ED481B-2021-059, Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; IN845D 2020/38, Xunta de Galicia; ED431G 2019/01, This research was funded by Instituto de Salud Carlos III, Government of Spain, DTS18/00136 research project; Ministerio de Ciencia e Innovación y Universidades, Government of Spain, RTI2018-095894-B-I00 research project; Ministerio de Ciencia e Innovación, Government of Spain through the research projects with references PID2019-108435RB-I00; TED2021-131201B-I00 and PDC2022-133132-I00; Consellería de Cultura, Educación e Universidade, Xunta de Galicia through the postdoctoral, grant ref. ED481B-2021-059; and Grupos de Referencia Competitiva, grant ref. ED431C 2020/24; Axencia Galega de Innovación (GAIN), Xunta de Galicia, grant ref. IN845D 2020/38; CITIC, as Research Center accredited by Galician University System, is funded by “Consellería de Cultura, Educación e Universidade from Xunta de Galicia”, supported in an 80 % through ERDF Funds, ERDF Operational Programme Galicia 2014–2020, and the remaining 20 % by “Secretaría Xeral de Universidades”, grant ref. ED431G 2019/01. Emilio López Varela acknowledges its support under FPI Grant Program through PID2019-108435RB-I00 project. Funding for open access charge: Universidade da Coruña/CISUG.
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Joint keypoint detection and description network for color fundus image registration

  • Rivas-Villar, David
  • Hervella, Álvaro S.
  • Rouco, José
  • Novo Buján, Jorge
[Absctract]: Background: Retinal imaging is widely used to diagnose many diseases, both systemic and eye-specific. In these cases, image registration, which is the process of aligning images taken from different viewpoints or moments in time, is fundamental to compare different images and to assess changes in their appearance, commonly caused by disease progression. Currently, the field of color fundus registration is dominated by classical methods, as deep learning alternatives have not shown sufficient improvement over classic methods to justify the added computational cost. However, deep learning registration methods are still considered beneficial as they can be easily adapted to different modalities and devices following a data-driven learning approach. Methods: In this work, we propose a novel methodology to register color fundus images using deep learning for the joint detection and description of keypoints. In particular, we use an unsupervised neural network trained to obtain repeatable keypoints and reliable descriptors. These keypoints and descriptors allow to produce an accurate registration using RANdom SAmple Consensus (RANSAC). We train the method using the Messidor dataset and test it with the Fundus Image Registration Dataset (FIRE) dataset, both of which are publicly accessible. Results: Our work demonstrates a color fundus registration method that is robust to changes in imaging devices and capture conditions. Moreover, we conduct multiple experiments exploring several of the method’s parameters to assess their impact on the registration performance. The method obtained an overall Registration Score of 0.695 for the whole FIRE dataset (0.925 for category S, 0.352 for P, and 0.726 for A). Conclusions: Our proposal improves the results of previous deep learning methods in every category and surpasses the performance of classical approaches in category A which has disease progression and thus represents the most relevant scenario for clinical practice as registration is commonly used in patients with diseases for disease monitoring purposes., This work was supported by Ministerio de Ciencia e Innovación, Government of Spain, through the RTI2018-095894-B-I00, PID2019-108435RB-I00, TED2021-131201B-I00, and PDC2022-133132-I00 research projects; Consellería de Cultura, Educación e Universidade Xunta de Galicia through the Grupos de Referencia Competitiva grant (Ref. ED431C 2020/24), the predoctoral fellowship (Ref. ED481A 2021/147) and the postdoctoral fellowship (Ref. ED481B-2022-025); CITIC, Centro de Investigación de Galicia (Ref. ED431G 2019/01), itself received financial support from Consellería de Educación, Universidade e Formación Profesional, Xunta de Galicia, through the ERDF (80%) and Secretaría Xeral de Universidades (20%)., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED481A 2021/147, Xunta de Galicia; ED481B-2022-025, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Multi-depth transfer learning-based approaches via generative models for foveal avascular zone segmentation in OCTA images

  • Regueiro Feal, Ángel
  • Goyanes, Elena
  • Moura, Joaquim de
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
This version of the article has been accepted for publication, after peer review. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The Version of Record is available online at: https://doi.org/10.1109/IJCNN64981.2025.11227613 Traballo presentado en:2025 International Joint Conference on Neural Networks (IJCNN), Roma, Italia, 30 June-05 July 2025, [Abstract]: The automatic identification and segmentation of the Foveal Avascular Zone (FAZ) is crucial for diagnosing and monitoring retinal diseases. However, the limited availability of Optical Coherence Tomography Angiography (OCTA) images with ground truth annotations poses a significant challenge for developing robust deep learning models. Traditional transfer learning techniques, such as ImageNet-based pre-training, require large datasets and struggle to adapt to domain-specific tasks in medical imaging. To address this issue, we propose a novel multi-deep transfer learning framework that leverages pretrained models on a generation task using both superficial (SCP) and deep capillary plexuses (DCP) of the retina. To the best of our knowledge, this is the first approach that integrates depth information from multiple vascular plexuses, allowing the model to capture cross-plexus structural relationships and enhance its ability to learn domain-specific vascular features while mitigating data scarcity constraints. We validated our framework through extensive experiments, demonstrating competitive or even superior segmentation performance compared to state-of-the-art pretraining models, despite using significantly smaller datasets. Our approach achieved a Dice coefficient score of 0.8238 ± 0.0263, a Jaccard Index of 0.7189 ± 0.0293, and a Correlation Index of 0.8328 ± 0.0229, highlighting the effectiveness of our multi-depth feature learning strategy in improving segmentation precision and generalization, even with limited data availability., This work was supported by Ministerio de Ciencia e Innovación, Government of Spain through the research project with [grant numbers PID2023- 148913OB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educación, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [grant number ED431C 2024/33], predoctoral grant [grant number ED481A-2023-152]. Also supported by the ISCIII under the grant [FORT23/00010] as part of the Programa FORTALECE of Ministerio de Ciencia e Innovación., Xunta de Galicia; ED431C 2024/33, Xunta de Galicia; ED481A-2023-152
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Automatic simultaneous ciliary muscle segmentation and biomarker extraction in AS-OCT images using deep learning-based approaches

  • Goyanes, Elena
  • Moura, Joaquim de
  • Fernández-Vigo, José Ignacio
  • Fernández-Vigo, José A.
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
[Abstract]: Recent clinical studies have emphasized the importance of understanding the morphology and mechanics of the ciliary muscle. The ciliary muscle plays a vital role in various functions related to the anterior segment of the eye, including the regulation of intraocular pressure and the maintenance of the shape of the crystalline lens. To advance research in this area, we propose a fully automated methodology for the segmentation and biomarker measurement of the ciliary muscle in two different scan depths (6 mm and 16 mm), which are commonly used by clinicians to analyze biomarkers. Our methodology aims to provide repeatable, and immediate results through an exhaustive analysis of different network architectures, encoders, and transfer learning strategies. We also extracted a comprehensive set of relevant biomarkers, including parameters that provide essential information about its behavior during the accommodation process, overall dimensions, and biomechanical properties. These biomarkers can help clinicians and researchers in the diagnoses and monitor of different ocular diseases such as glaucoma, myopia, and presbyopia and develop new therapeutic strategies, potentially leading to more effective treatments and improved patient outcomes. Our methodology achieved accurate qualitative and quantitative results, with high accuracy values of 0.9665 ± 0.1280 and 0.9772 ± 0.0873 for the best combinations for 6 mm and 16 mm, respectively. Our proposed system provides a valuable and automatic tool for clinicians and researchers in the segmentation and analysis of the ciliary muscle in AS-OCT images., This work was supported by Ministerio de Ciencia e Innovación, Government of Spain through the research project with [grant numbers RTI2018-095894-B-I00, PID2019-108435RB-I00, TED2021-131201B–I00, and PDC2022-133132-I00]; Consellería de Educación, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [grant number ED431C 2020/24]; predoctoral grant [grant number ED481A-2023-152]; CITIC, Centro de Investigación de Galicia [grant number ED431G 2019/01], receives financial support from Consellería de Educación, Universidade e Formación Profesional, Xunta de Galicia, through the ERDF (80%) and Secretaría Xeral de Universidades (20%). Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED481A-2023-152, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Computer-assisted evaluation of retinal vessel tortuosity in children with sickle cell disease without retinopathy

  • Raffa, Lina H.
  • Raffa, Enass H.
  • S. Hervella, Álvaro
  • Ramos, Lucía
  • Novo Buján, Jorge
  • Rouco, José
  • Ortega Hortas, Marcos
This version of the article has been accepted for publication. The Version of Record is available online at https://doi.org/10.1016/j.mvr.2024.104752., [Abstract]: Objective: We assessed the predictive efficacy of automatically quantified retinal vascular tortuosity from the fundus pictures of patients with sickle cell disease (SCD) without evident retinopathy. Methods: Retinal images were obtained from 31 healthy and 31 SCD participants using fundus imaging and analyzed using a novel computational automated metric assessment. The local and global vessel tortuosity and their relationship with systemic disease parameters were analyzed based on the images. Results: SCD arteries had an increased local tortuosity index compared to the controls (0.0007 ± 0.0019 vs. 0.0006 ± 0.0014, p = 0.019). Furthermore, the SCD patients had wider vessel caliber mainly in the arteries (14.68 ± 5.3 vs. 14.06 ± 5.3, p < 0.001). The SCD global tortuosity did not differ significantly from that of the controls (p = 0.598). The female participants had significantly reduced retinal vessel tortuosity indices compared to the male participants (p = 0.018). Conclusion: Retinal arterial tortuosity and caliber were reliable and objective measures that could be used as a non-invasive prognostic and diagnostic indicator in sickle cell retinopathy. Further studies are required to correlate these local vascular parameters to systemic risk factors and monitor their progression and change over time., This work was supported by Ministerio de Ciencia, Innovación y Universidades, Government of Spain, through the PID2023-148913OB-I00, TED2021-131201B-I00, and PDC2022-133132-I00 research projects; Consellería de Cultura, Educación e Universidade, Xunta de Galicia, through Grupos de Referencia Competitiva (ref. ED431C 2024/33) and a postdoctoral fellowship (ref. ED481B-2022-025); and Instituto de Salud Carlos III (ISCIII) under grant FORT23/00010 as part of the Ministerio de Ciencia, Innovación y Universidades Program., Xunta de Galicia; ED431C 2024/33, Xunta de Galicia; ED481B-2022-025
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Deep feature analysis in a transfer learning approach for the automatic COVID-19 screening using chest X-ray images

  • Iglesias Morís, Daniel
  • Moura, Joaquim de
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
[Abstract]: COVID-19 is a challenging disease that was declared as global pandemic in March 2020. As the main impact of this disease is located in the pulmonary regions, chest X-ray devices are very useful to understand the severity of the disease on each patient. In order to reduce the risk of cross-contamination, the radiologists are recommended to use portable devices instead of fixed machinery, as these devices are easier to decontaminate. Moreover, the development of reliable and robust methodologies of computer-aided diagnosis systems is very relevant to reduce the workload that expert clinicians are experiencing in the current moment. In this work, we propose a comprehensive analysis of the deep features extracted from portable chest X-ray captures to perform a COVID-19 screening. We also study the optimal characterization of the problem with a lower dimensionality, contrasting the results of the feature selection methods that were chosen. Results demonstrated that the proposed approach is robust and reliable, obtaining a 90.43% of accuracy for the test set, using only 46.85% of the deep features in the context of poor quality and low detail X-ray images obtained from portable devices., This work was supported by Ministerio de Ciencia e Innovación, Government of Spain through the research project with [grant numbers RTI2018-095894-B-I00, PID2019-108435RB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educación, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [grant number ED431C 2020/24], predoctoral grant [grant number ED481A 2021/196]; CITIC, Centro de Investigación de Galicia [grant number ED431G 2019/01], receives financial support from Consellería de Educación, Universidade e Formación Profesional, Xunta de Galicia, through the ERDF (80%) and Secre-taría Xeral de Universidades (20%)., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED481A 2021/196, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Sistema automático para la evaluación de enfermedades neurodegenerativas en imágenes OCT mediante deep learning

  • Álvarez-Rodríguez, Lorena
  • Pueyo-Bestué, Ana
  • Moura, Joaquim de
  • Viladés, Elisa
  • García-Martín, Elena
  • Sánchez, Clara I.
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
O IDIS, INIBIC e IIS Galicia Sur organizaron Biointegrasaúde 2023, celebrado no Complexo Hospitalario Universitario de A Coruña (CHUAC), 14 de dicembro de 2023., El Alzhéimer (AD), el temblor esencial (ET), la esclerósis múltiple (MS) o el Párkinson (PD) son enfermedades neurodegenerativas (END) que están correlacionadas con cambios en algunas capas retinales clave. Las tomografías de coherencia óptica (OCT) pueden proporcionar información detallada desde diferentes perspectivas para analizar esas capas. Proponemos un sistema automático que: Segmenta las capas RNFL y GCL-BM de vólumenes 3D e imágenes OCT retinales de mácula y disco óptico. Extrae biomarcadores computacionales como deep features o grosor. Hace un cribado combinando información de ambas vistas OCT., Esta investigación ha sido subvencionada por el Instituto de Salud Carlos III, Gobierno de Spain, [proyectos de investigación PI17/01726 y PI20/00437]; Inflammatory Disease Network (RICORS) [proyecto RD21/0002/0050]; Ministerio de Ciencia e Innovación, Gobierno de Spain [proyectos de investigación PDC2022-133132-I00, PID2019-108435RB-I00 y TED2021-131201B-I00]; Consellería de Cultura, Educación e Universidade, Xunta de Galicia, a través de Grupos de Referencia Competitiva [subvención ED431C 2020/24]. Las organizaciones financiadoras no participaron en el dise˜no o ejecución de esta investigación., Gobierno de Aragón; RD21/0002/0050, Xunta de Galicia; ED431C 2020/24
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Explainable learning to analyze the outcome of COVID-19 patients using clinical data

  • Olañeta Fariña, Daniel
  • Iglesias Morís, Daniel
  • Moura, Joaquim de
  • Marcos, Pedro J.
  • Míguez-Rey, Enrique
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
[Abstract]: Patients at high risk of contracting COVID-19 require specialized monitoring throughout their illness to ensure optimal treatment at each stage. To support this monitoring, Computer-Aided Diagnosis (CAD) methods analyze clinical data to estimate the most likely outcome for each patient, using various clinical variables such as symptoms, medical history, and laboratory results to predict outcomes. Despite the numerous proposals for COVID-19 diagnosis using CAD methods, the lack of explainability in many machine learning models poses a challenge in incorporating these methods into clinical practice. Additionally, other crucial tasks such as estimating the risk of death or severe forms of the disease must be considered to identify cases that require greater monitoring. To overcome these challenges, we propose an explainable methodology for estimating the risk of hospitalization and death in COVID-19 patients using clinical data. Our methodology employs four machine learning algorithms, three feature selection methods, and a decision tree to provide explainability. Our approach achieves an accuracy of 86.16% ± 0.74% for the estimation of hospitalization risk with 29 features, and an accuracy of 86.40% ± 1.80% for the estimation of the risk of death with 26 features. Moreover, our methodology provides valuable insights into the relationship between clinical variables and patient outcomes, which can inform more robust and informed clinical decision-making and improve our understanding of the disease. We demonstrate the potential of our transparent and effective CAD methods to support clinical decision-making in COVID-19 patient care and further research, offering a promising solution to overcome the challenges in incorporating CAD methods into clinical practice., This work was supported by Ministerio de Ciencia e Innovación, Government of Spain through the research project with [grant numbers RTI2018-095894-B-I00, PID2019-108435RB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educación, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [grant number ED431C 2020/24], predoctoral grant [grant number ED481A 2021/196]; CITIC, Centro de Investigación de Galicia [grant number ED431G 2019/01], receives financial support from Con-sellería de Educación, Universidade e Formación Profesional, Xunta de Galicia, through the ERDF (80%) and Secre-taría Xeral de Universidades (20%)., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED481A 2021/196, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Evolutionary multi-target neural network architectures for flow void analysis in optical coherence tomography angiography

  • López-Varela, Emilio
  • Moura, Joaquim de
  • Novo Buján, Jorge
  • Fernández-Vigo, José Ignacio
  • Moreno-Morillo, Francisco Javier
  • García-Feijóo, Julián
  • Ortega Hortas, Marcos
[Abstract]: Optical coherence tomography angiography (OCTA) is a non-invasive imaging modality used to evaluate the retinal microvasculature. Recent advances in OCTA allows to visualize the blood flow within the choriocapillaris region, where a granular image is obtained showing a pattern of small dark regions, called flow voids (FVs). Given its relevance, numerous clinical studies have linked the changes in FVs distribution to multiple diseases. The granular structure of these images makes accurate labeling and segmentation difficult, which can be overcome by using a multi-target perspective. However, manually designing a neural architecture that can accurately predict all targets in a balanced way is a major challenge. In this work, we propose a novel methodology based on evolutionary multi-target optimized networks that, through a set of evolutionary operators, traverses a search space of architectures in a deep but efficient way. This methodology allows us to discover efficient and accurate multi-target architectures tailored to our problem, but which are also adaptable to other tasks due to their robustness. To validate and analyze our methodology and the discovered network model, we performed extensive experimentation with cases from a real clinical study, achieving better results than the state of the art and manually designed architectures., This research was funded by Government of Spain, Ministerio de Ciencia e Innovación y Universidades, Government of Spain, RTI2018- 095894-B-I00 research project; Ministerio de Ciencia e Innovación, Government of Spain through the research projects with reference PID2019-108435RB-I00, reference PDC2022-133132-I00 and TED2021- 131201B-I00; Consellería de Cultura, Educación e Universidade, Xunta de Galicia through the Grupos de Referencia Competitiva, grant ref. ED431C 2020/24; CITIC, as Research Center accredited by Galician University System, is funded by ‘‘Consellería de Cultura, Educación e Universidade from Xunta de Galicia’’, supported in an 80% through ERDF Funds, ERDF Operational Programme Galicia 2014–2020, and the remaining 20% by ‘‘Secretaría Xeral de Universidades’’, grant ref. ED431G 2019/01. Emilio López Varela acknowledges its support under FPI Grant Program through PID2019-108435RB-I00 project. Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED431G 2019/01, Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Recurrent Task Specialization Network for Segmentation-aided Vascular Landmarks Detection in Retinal Images

  • Hervella, Álvaro S.
  • Rouco, José
  • Novo Buján, Jorge
  • Sánchez, Clara I.
  • Ortega Hortas, Marcos
Presented at the 27th European Conference on Artificial Intelligence, ECAI 2024, Santiago de Compostela 19-24 October 2024., [Abstract]: The detection of vessel crossings and bifurcations in eye fundus images plays an important role in numerous applications, including the diagnosis of ophthalmic and systemic diseases, biometric authentication, and retinal image registration. Nowadays, deep neural networks are successfully used for the detection of these vascular landmarks. However, existing approaches could be limited by the lack of understanding of the retinal anatomy and the intricate retinal vasculature. In this context, we propose Recurrent Task Specialization, a novel approach that performs a recurrent forward process with two forward passes through the same network, each of them specialized in a different task. We apply the proposed approach to the detection of vessel crossings and bifurcations in the retina via heatmap regression, using the segmentation of the retinal vasculature as the auxiliary task. To validate our proposal, we perform comparative experiments on two public datasets, including common alternatives to leverage auxiliary tasks, such as standard multi-task learning and transfer learning. The proposed approach outperforms existing alternatives and achieves the best results in the state-of-the-art for the detection of vessel crossings and bifurcations in retinal images. In this regard, our experiments demonstrate the potential of the proposed approach to improve the performance of deep neural networks in applications where adequate auxiliary tasks can be constructed., This work is supported by Ministerio de Ciencia e Innovación, Government of Spain, through the PID2019-108435RB-I00, TED2021-131201B-I00, and PDC2022-133132-I00 research projects; Consellería de Cultura, Educación e Universidade, Xunta de Galicia, through Grupos de Referencia Competitiva ref. ED431C 2020/24 and the postdoctoral fellowship ref. ED481B-2022-025; and Instituto de Salud Carlos III under the grant [FORT23/00010] as part of Programa FORTALECE from Ministerio de Ciencia e Innovación., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED481B-2022-025
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Robust multi-view approaches for retinal layer segmentation in glaucoma patients via transfer learning

  • Gende, M.
  • Moura, Joaquim de
  • Fernández-Vigo, José Ignacio
  • Martínez-de-la-Casa, José María
  • García-Feijóo, Julián
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
[Absctract]: Background: Glaucoma is the leading global cause of irreversible blindness. Glaucoma patients experience a progressive deterioration of the retinal nervous tissues that begins with a loss of peripheral vision. An early diagnosis is essential in order to prevent blindness. Ophthalmologists measure the deterioration caused by this disease by assessing the retinal layers in different regions of the eye, using different optical coherence tomography (OCT) scanning patterns to extract images, generating different views from multiple parts of the retina. These images are used to measure the thickness of the retinal layers in different regions. Methods: We present two approaches for the multi-region segmentation of the retinal layers in OCT images of glaucoma patients. These approaches can extract the relevant anatomical structures for glaucoma assessment from three different OCT scan patterns: circumpapillary circle scans, macular cube scans and optic disc (OD) radial scans. By employing transfer learning to take advantage of the visual patterns present in a related domain, these approaches use state-of-the-art segmentation modules to achieve a robust, fully automatic segmentation of the retinal layers. The first approach exploits inter-view similarities by using a single module to segment all of the scan patterns, considering them as a single domain. The second approach uses view-specific modules for the segmentation of each scan pattern, automatically detecting the suitable module to analyse each image. Results: The proposed approaches produced satisfactory results with the first approach achieving a dice coefficient of 0.85±0.06 and the second one 0.87±0.08 for all segmented layers. The first approach produced the best results for the radial scans. Concurrently, the view-specific second approach achieved the best results for the better represented circle and cube scan patterns. Conclusions: To the extent of our knowledge, this is the first proposal in the literature for the multi-view segmentation of the retinal layers of glaucoma patients, demonstrating the applicability of machine learning-based systems for aiding in the diagnosis of this relevant pathology., This work was supported by Ministerio de Ciencia e Innovación y Universidades, Government of Spain (grant number RTI2018-095894-B-I00); Ministerio de Ciencia e Innovación, Government of Spain through the research project with (grant numbers PID2019-108435RB-I00, TED2021-131201B-I00, and PDC2022-133132-I00); Consellería de Cultura, Educación, Formación Profesional e Universidades, Xunta de Galicia, Grupos de Referencia Competitiva (grant number ED431C 2020/24), predoctoral grant (grant number ED481A 2021/161); CITIC, Centro de Investigación de Galicia (grant number ED431G 2019/01), and receives financial support from Consellería de Cultura, Educación, Formación Profesional e Universidades, Xunta de Galicia, through the ERDF (80%) and Secretaría Xeral de Universidades (20%)., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED481A 2021/161, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Circumpapillary OCT-based multi-sector analysis of retinal layer thickness in patients with glaucoma and high myopia

  • Gende, M.
  • Moura, Joaquim de
  • Robles, Patricia
  • Fernández-Vigo, José Ignacio
  • Martínez-de-la-Casa, José María
  • García-Feijóo, Julián
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
[Abstract]: Glaucoma is the leading cause of irreversible blindness worldwide. The diagnosis process for glaucoma involves the measurement of the thickness of retinal layers in order to track its degeneration. The elongated shape of highly myopic eyes can hinder this diagnosis process, since it affects the OCT scanning process, producing deformations that can mimic or mask the degeneration caused by glaucoma. In this work, we present the first comprehensive cross-disease analysis that is focused on the anatomical structures most impacted in glaucoma and high myopia patients, facilitating precise differential diagnosis from those solely afflicted by myopia. To achieve this, a fully automatic approach for the retinal layer segmentation was specifically tailored for the accurate measurement of retinal thickness in both highly myopic and emmetropic eyes. To the best of our knowledge, this is the first approach proposed for the analysis of retinal layers in circumpapillary optical coherence tomography images that takes into account the elongation of the eyes in myopia, thus addressing critical diagnostic needs. The results from this study indicate that the temporal superior (mean difference 11.1 µm, p < 0.05, nasal inferior (13.1 µm, p < 0.01) and temporal inferior (13.3 µm, p < 0.01) sectors of the retinal nerve fibre layer show the most significant reduction in retinal thickness in patients of glaucoma and myopia with regards to patients of myopia., This research was funded by Ministerio de Ciencia e Innovación, Government of Spain [research projects PDC2022-133132-I00,TED2021-131201B-I00, and PID2023-148913OB-I00]; Consellería de Cultura, Educación e Universidade, Xunta de Galicia, through Grupos de Referencia Competitiva [grant number ED431C 2024/33], predoctoral grant [grant number ED481A 2021/161]. This work was supported by the Instituto de Salud Carlos III (ISCIII) under the grant [FORT23/00010] as part of the Programa FORTALECE of Ministerio de Ciencia e Innovación and research project [PI23/00828]: Desarrollo evaluación de un algoritmo de detección de glaucoma a partir de un abordaje multimodal en pacientes con miopía magna, as well as Thea Research Grant 2022-2024. The funding organisations had no role in the design or conduct of this research. Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431C 2024/33, Xunta de Galicia; ED481A 2021/161
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Semantic-guided generative latent diffusion augmentation approaches for improving the neovascularization diagnosis in OCT-A imaging

  • Iglesias Morís, Daniel
  • Moura, Joaquim de
  • Carmona, Enrique J.
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
This is the Accepted version of the article: Morís, D. I., de Moura, J., Carmona, E. J., Novo, J., & Ortega, M. (2025). ‘Semantic-guided generative latent diffusion augmentation approaches for improving the neovascularization diagnosis in OCT-A imaging’ published in: Pattern Recognition Letters, 189, p. 31-37. The Version of Record is available online at https://doi.org/10.1016/j.patrec.2025.01.003., [Abstract]: Age-related Macular Degeneration (AMD) presents an enormous challenge in Western Societies due to the increase in life expectancy. AMD is characterized for causing Macular Neovascularization. Optical Coherence Tomography Angiography (OCT-A) represents an advanced method to help find evidence of the disease. In this context, deep learning algorithms are suitable to make a screening of the disease. However, biomedical imaging domains are usually affected by the data scarcity issue. The mitigation of this problem can be achieved with the support of generative latent diffusion models. This represents a powerful strategy to artificially augment the cardinality of the original dataset. In this work, we present a novel fully automatic methodology to generate OCT-A images, guided by semantic information, to reduce the impact of data scarcity and to enable an accurate neovascularization diagnosis. The evaluation has been performed with a specific dataset composed of two different fields of view commonly used by clinicians. The results demonstrate a top accuracy of 96.50% 1.37%, using 3 × 3 scans, and 95.79% 1.44%, when using 6 × 6 scans. The proposed methodology has great potential to be extrapolated to other imaging modalities and domains., This work received funding from the Ministerio de Ciencia e Innovación (MCI) through the grants [PID2023-148913OB-I00], [TED2021-131201B-I00], and [PDC2022-133132-I00], and from the Consellería de Educación, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, under grant [ED431C 2024/33]. Additional support was provided by the Instituto de Salud Carlos III under grant [FORT23/00010], as part of the Programa FORTALECE from the MCI. This work was also supported by the Horizon Europe Programme through the ACHILLES/101189689 project (HORIZON-CL4-2024-DATA-01-01)., Xunta de Galicia; ED431C 2024/33
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Enhanced multiple sclerosis diagnosis using high-resolution 3D OCT volumes with synthetic slices

  • López-Varela, Emilio
  • Olivier Pascual, Nuria
  • Quezada-Sánchez, Johnny
  • Oreja-Guevara, Celia
  • Santos Bueso, Enrique
  • Barreira, Noelia
[Abstract]: Optical Coherence Tomography (OCT), known for its micron-level resolution and non-invasive nature, is essential in diagnosing Multiple Sclerosis (MS). Accurate MS diagnosis through OCT is facilitated by identifying changes in retinal layer thickness, which serve as biomarkers, such as the retinal nerve fiber layer and the macular ganglion cell layer. To adequately diagnose MS, it is crucial to detect thickness changes in specific small regions of the retina, necessitating extensive retinal coverage with minimal granularity. However, a significant challenge in using OCT for MS diagnosis is the inverse relationship between the number of slices and the image quality of OCT volumes. High-resolution images require longer acquisition times, which limits the number of slices that can be obtained and results in covering a smaller area of the retina. Conversely, increasing the number of slices reduces individual image quality, impairing the detection of retinal layer structures. To address this issue, we propose a novel approach for the automatic detection of MS using high-resolution synthetic 3D OCT volumes. Our methodology involves using a generative network to synthesize intermediate slices, thereby enhancing retinal coverage without degrading image quality. This synthetic augmentation improves cross-sectional resolution, providing more comprehensive retinal details. Then we use a segmentation network to extract biomarkers and multiple 3D classification models to directly detect MS automatically. Our results demonstrate significant improvements in accuracy and reliability. Integrating synthetic slices into OCT volumes enhances the detection of MS, underscoring the potential of generative models for better clinical outcomes in MS diagnosis., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED431G 2019/01, This research was funded by Government of Spain, Ministerio de Ciencia e Innovación y Universidades, Government of Spain, RTI2018- 095894-B-I00 research project; Ministerio de Ciencia e Innovación, Government of Spain through the research projects with reference PID2019-108435RB-I00, reference PDC2022-133132-I00 and TED2021-131201B-I00; Consellería de Cultura, Educación e Universi- dade, Xunta de Galicia through the Grupos de Referencia Competitiva, grant ref. ED431C 2020/24; CITIC, as Research Center accredited by Galician University System, is funded by ‘‘Consellería de Cultura, Educación e Universidade from Xunta de Galicia’’, supported in an 80% through ERDF Funds, ERDF Operational Programme Galicia 2014– 2020, and the remaining 20% by ‘‘Secretaría Xeral de Universidades’’, grant ref. ED431G 2019/01. Emilio López Varela acknowledges its support under FPI Grant Program through PID2019-108435RB-I00 project.
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Enhancing Pathological Detection and Monitoring in OCT Volumes with Limited Slices using Convolutional Neural Networks and 3D Visualization Techniques

  • López-Varela, Emilio
  • Barreira, Noelia
  • Olivier Pascual, Nuria
  • Penedo, Manuel
Cursos e Congresos, C-155, [Abstract] Optical Coherence Tomography (OCT) is a non-invasive imaging technique with a crucial role in the monitoring of a wide range of diseases. In order to make a good diagnosis it is essential that clinicians can observe any subtle changes that appear in the multiple ocular structures, so it is imperative that the 3D OCT volumes have good resolution in each axis. Unfortunately, there is a trade-off between image quality and the number of volume slices. In this work, we use a convolutional neural network to generate the intermediate synthetic slices of the OTC volumes and we propose a few variants of a 3D reconstruction algorithm to create visualizations that emphasize the changes present in multiple retinal structures to aid clinicians in the diagnostic process, Xunta de Galicia; ED431C 2020/24, This research was funded by Government of Spain, Ministerio de Ciencia e Innovación y Universidades, Government of Spain, RTI2018-095894-B-I00 research project; Ministerio de Ciencia e Innovación, Government of Spain through the research projects with reference PID2019-108435RB-I00, PDC2022-133132-I00 and TED2021-131201B-I00; Consellería de Cultura, Educación e Universidade, Xunta de Galicia through the Grupos de Referencia Competitiva, grant ref. ED431C 2020/24; CITIC, as Research Center accredited by Galician University System, is funded by ”Consellería de Cultura, Educación e Universidade from Xunta de Galicia”, supported in an 80% through ERDF Funds, ERDF Operational Programme Galicia 2014-2020, and the remaining 20% by ”Secretaría Xeral de Universidades”, grant ref. ED431G 2019/01. Emilio López Varela acknowledges its support under FPI Grant Program through PID2019-108435RB-I00 project.
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Automatic Segmentation of Retinal Layers in Multiple Neurodegenerative Disorder Scenarios

  • Gende, M.
  • Mallén Gracia, Victor
  • Moura, Joaquim de
  • Cordón Ciordia, Beatriz
  • García-Martín, Elena
  • Sánchez, Clara I.
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
Open Access provided by ‘Universidade da Coruña/CISUG’ within the CRUI-CARE Agreement, [Absctract]: Retinal Optical Coherence Tomography (OCT) allows the non-invasive direct observation of the central nervous system, enabling the measurement and extraction of biomarkers from neural tissue that can be helpful in the assessment of ocular, systemic and Neurological Disorders (ND). Deep learning models can be trained to segment the retinal layers for biomarker extraction. However, the onset of ND can have an impact on the neural tissue, which can lead to the degraded performance of models not exposed to images displaying signs of disease during training. We present a fully automatic approach for the retinal layer segmentation in multiple neurodegenerative disorder scenarios, using an annotated dataset of patients of the most prevalent NDs: Alzheimer's disease, Parkinson's disease, multiple sclerosis and essential tremor, along with healthy control patients. Furthermore, we present a two-part, comprehensive study on the effects of ND on the performance of these models. The results show that images of healthy patients may not be sufficient for the robust training of automated segmentation models intended for the analysis of ND patients, and that using images representative of different NDs can increase the model performance. These results indicate that the presence or absence of patients of ND in datasets should be taken into account when training deep learning models for retinal layer segmentation, and that the proposed approach can provide a valuable tool for the robust and reliable diagnosis in multiple scenarios of ND., This work was supported in part by Instituto de Salud Carlos III, Government of Spain, under Grants PI17/01726 and PI20/00437, in part by Inflammatory Disease Network (RICORS) under Grant RD21/0002/0050, in part by the Ministerio de Ciencia e Innovación, Government of Spain under Grants PDC2022-133132-I00, RTI2018-095894-B-I00, PID2019- 108435RB-I00, and TED2021-131201B-I00, in part by the Consellería de Cultura, Educación e Universidade, Xunta de Galicia through Grupos de Referencia Competitiva under Grant ED431C 2020/24 and predoctoral under Grant ED481A 2021/161, in part by CITIC, Centro de Investigación de Galicia under Grant ED431G 2019/01, and in part by Consellería de Educación, Universidade e Formación Profesional, Xunta de Galicia through the ERDF (80%) and Secretaría Xeral de Universidades (20%)., Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Multi-Adaptive Optimization for multi-task learning with deep neural networks

  • Hervella, Álvaro S.
  • Rouco, José
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: Multi-task learning is a promising paradigm to leverage task interrelations during the training of deep neural networks. A key challenge in the training of multi-task networks is to adequately balance the complementary supervisory signals of multiple tasks. In that regard, although several task-balancing approaches have been proposed, they are usually limited by the use of per-task weighting schemes and do not completely address the uneven contribution of the different tasks to the network training. In contrast to classical approaches, we propose a novel Multi-Adaptive Optimization (MAO) strategy that dynamically adjusts the contribution of each task to the training of each individual parameter in the network. This automatically produces a balanced learning across tasks and across parameters, throughout the whole training and for any number of tasks. To validate our proposal, we perform comparative experiments on real-world datasets for computer vision, considering different experimental settings. These experiments allow us to analyze the performance obtained in several multi-task scenarios along with the learning balance across tasks, network layers and training steps. The results demonstrate that MAO outperforms previous task-balancing alternatives. Additionally, the performed analyses provide insights that allow us to comprehend the advantages of this novel approach for multi-task learning., This work is supported by Ministerio de Ciencia e Innovación, Government of Spain, through the RTI2018-095894-B-I00, PID2019-108435RB-I00, TED2021-131201B-I00, and PDC2022-133132-I00 research projects; Consellería de Cultura, Educación e Universidade, Xunta de Galicia, through Grupos de Referencia Competitiva ref. ED431C 2020/24 and the postdoctoral fellowship ref. ED481B-2022-025. CITIC, Centro de Investigación de Galicia ref. ED431G 2019/01, receives financial support from Consellería de Cultura, Educación e Universidade, Xunta de Galicia, through the ERDF of the European Union (80%) and Secretaría Xeral de Universidades (20%). Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED481B-2022-025, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Efficient semi-supervised hierarchical training for segmenting choroidal vessels and other structures on OCT images of multiple sclerosis patients

  • López-Varela, Emilio
  • Olivier Pascual, Nuria
  • Quezada-Sánchez, Johnny
  • Oreja-Guevara, Celia
  • Barreira, Noelia
[Abstract]: Optical coherence tomography (OCT) is a non-invasive imaging technique used to diagnose ocular and systemic diseases. Recently, several clinical studies have linked changes in different ocular layers to the development of multiple sclerosis (MS), so accurate segmentation of these structures has become an essential task. Unfortunately, segmenting the entire set of structures involved is a very difficult task, due to their large number and variability. These two factors hinder the labeling of images and therefore severely restrict the ability to achieve a large dataset with all structures manually annotated, limiting the use of a standard supervised approach. In this paper, we propose a semi-supervised learning methodology to robustly segment ocular structures in OCT images using a limited number of partially labeled images. Our methodology maximizes the information we can extract from labeled images through hierarchical learning, where multiple decoders are used to extract segmented structures progressively. We use a reconstruction loss function to provide structural coherence to the segmentation and a teacher–student strategy to effectively leverage the information present in the set of unlabeled images. In addition to the segmentation of labeled structures, this hierarchical approach allows segmenting structures that are not labeled in the dataset such as the choroidal vessels. To validate the proposed methodology, we have carried out extensive experimentation using two datasets with different characteristics. These experiments have demonstrated a great potential of this methodology to train networks efficiently with partially labeled images, which allows to accurately extract the main biomarkers linked to the development of MS., This research was funded by Government of Spain, Ministerio de Ciencia e Innovación y Universidades, Government of Spain, RTI2018-095894-B-I00 research project; Ministerio de Ciencia e Innovación, Government of Spain through the research projects with reference PID2019-108435RB-I00, PDC2022-133132-I00 and TED2021-1312 01B-I00; Consellería de Cultura, Educación e Universidade, Xunta de Galicia through the Grupos de Referencia Competitiva, grant ref. ED431C 2020/24; CITIC, as Research Center accredited by Galician University System, is funded by ‘‘Consellería de Cultura, Educación e Universidade from Xunta de Galicia, Spain’’, supported in an 80% through ERDF Funds, ERDF Operational Programme Galicia 2014–2020, and the remaining 20% by ‘‘Secretaría Xeral de Universidades, Spain’’, grant ref. ED431G 2019/01. Emilio López Varela acknowledges its support under FPI, Spain Grant Program through PID2019-108435RB-I00 project., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Sistema automático para la predicción de la respuesta a la terapia fotodinámica en la coriorretinopatía serosa central

  • Goyanes, Elena
  • Moura, Joaquim de
  • Fernández-Vigo, José Ignacio
  • García-Feijóo, Julián
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
[Resumen] Se presenta un innovador método de deep learning para la segmentación automatizada en 3D de las regiones de fluido en imágenes de Tomografía de Coherencia ´Óptica (OCT) de pacientes con coriorretinopatía serosa central (CSCR), seguida de un análisis de respuesta a la Terapia Fotodinámica (PDT) en pacientes con CSCR. Este método no solo reduce sustancialmente el tiempo y esfuerzo requeridos para la segmentación, sino que también ofrece una técnica estandarizada, fomentando estudios de investigación a gran escala. Para llevar a cabo el trabajo utilizamos un conjunto de datos robusto compuesto por 2,769 imágenes OCT, logrando resultados altamente satisfactorios que superan a las demás propuestas del estado del arte. Esta investigación impulsa la integración del deep learning en la práctica clínica, mejorando la gestión de la CSCR al permitir la formulación de estrategias de tratamiento personalizadas y una atención optimizada al paciente., Este trabajo está financiado por el Ministerio de Ciencia e Innovación, Gobierno de España por medio del proyecto de investigación con los códigos [RTI2018-095894-B-I00, PID2019-108435RB-I00, TED2021-131201B-I00 y PDC2022-133132-I00]; Consellería de Educación, Universidade e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [código ED431C 2020/24], ayuda predoctoral [ED481A-2023-152]., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED481A-2023-152
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Explainable artificial intelligence for the automated assessment of the retinal vascular tortuosity

  • Hervella, Álvaro S.
  • Ramos, Lucía
  • Rouco, José
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: Retinal vascular tortuosity is an excessive bending and twisting of the blood vessels in the retina that is associated with numerous health conditions. We propose a novel methodology for the automated assessment of the retinal vascular tortuosity from color fundus images. Our methodology takes into consideration several anatomical factors to weigh the importance of each individual blood vessel. First, we use deep neural networks to produce a robust extraction of the different anatomical structures. Then, the weighting coefficients that are required for the integration of the different anatomical factors are adjusted using evolutionary computation. Finally, the proposed methodology also provides visual representations that explain the contribution of each individual blood vessel to the predicted tortuosity, hence allowing us to understand the decisions of the model. We validate our proposal in a dataset of color fundus images providing a consensus ground truth as well as the annotations of five clinical experts. Our proposal outperforms previous automated methods and offers a performance that is comparable to that of the clinical experts. Therefore, our methodology demonstrates to be a viable alternative for the assessment of the retinal vascular tortuosity. This could facilitate the use of this biomarker in clinical practice and medical research., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This work is supported by Ministerio de Ciencia e Innovación, Government of Spain (RTI2018-095894-B-I00, PID2019-108435RB-I00, TED2021-131201B-I00, and PDC2022-133132-I00 research projects); Consellería de Cultura, Educación e Universidade, Xunta de Galicia (Grupos de Referencia Competitiva ref. ED431C 2020/24 and postdoctoral fellowship ref. ED481B-2022-025). CITIC, Centro de Investigación de Galicia ref. ED431G 2019/01, receives financial support from Consellería de Cultura, Educación e Universidade, Xunta de Galicia, through the ERDF of the European Union (80%) and Secretaría Xeral de Universidades (20%). Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED481B-2022-025, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Fully automatic deep convolutional approaches for the screening of neurodegeneratives diseases using multi-view OCT images

  • Álvarez-Rodríguez, Lorena
  • Pueyo-Bestué, Ana
  • Moura, Joaquim de
  • Viladés, Elisa
  • García-Martín, Elena
  • Sánchez, Clara I.
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
[Abstract]: The prevalence of neurodegenerative diseases (NDDs) such as Alzheimer’s (AD), Parkinson’s (PD), Essential tremor (ET), and Multiple Sclerosis (MS) is increasing alongside the aging population. Recent studies suggest that these disorders can be identified through retinal imaging, allowing for early detection and monitoring via Optical Coherence Tomography (OCT) scans. This study is at the forefront of research, pioneering the application of multi-view OCT and 3D information to the neurological diseases domain. Our methodology consists of two main steps. In the first one, we focus on the segmentation of the retinal nerve fiber layer (RNFL) and a class layer grouping between the ganglion cell layer and Bruch’s membrane (GCL-BM) in both macular and optic disc OCT scans. These are the areas where changes in thickness serve as a potential indicator of NDDs. The second phase is to select patients based on information about the retinal layers. We explore how the integration of both views (macula and optic disc) improves each screening scenario: Healthy Controls (HC) vs. NDD, AD vs. NDD, ET vs. NDD, MS vs. NDD, PD vs. NDD, and a final multi-class approach considering all four NDDs. For the segmentation task, we obtained satisfactory results for both 2D and 3D approaches in macular segmentation, in which 3D performed better due to the inclusion of depth and cross-sectional information. As for the optic disc view, transfer learning did not improve the metrics over training from scratch, but it did provide a faster training. As for screening, 3D computational biomarkers provided better results than 2D ones, and multi-view methods were usually better than the single-view ones. Regarding separability among diseases, MS and PD were the ones that provided better results in their screening approaches, being also the most represented classes. In conclusion, our methodology has been successfully validated with an extensive experimentation of configurations, techniques and OCT views, becoming the first multi-view analysis that merges data from both macula-centered and optic disc-centered perspectives. Besides, it is also the first effort to examine key retinal layers across four major NDDs within the framework of pathological screening., This research was funded by Instituto de Salud Carlos III, Government of Spain, [research projects PI17/01726 and PI20/00437]; Inflammatory Disease Network (RICORS) [research project RD21/0002/0050]; Ministerio de Ciencia e Innovación, Government of Spain through the research project with grant numbers [PID2023-148913OB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educación, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [grant number ED431C 2024/33]. Furthermore, this work was supported by the Instituto de Salud Carlos III (ISCIII) under the grant [FORT23/00010] as part of the Programa FORTALECE of Ministerio de Ciencia e Innovación. The funding organisations had no role in the design or conduct of this research., Gobierno de Aragón; RD21/0002/0050, Xunta de Galicia; ED431C 2024/33
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Geometric Deep Learning for Essential Tremor Screening Using

  • Álvarez-Rodríguez, Lorena
  • Moura, Joaquim de
  • Viladés, Elisa
  • García-Martín, Elena
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
This version of the article has been accepted for publication, after peer review. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The Version of Record is available online at: https://doi.org/10.1109/IJCNN64981.2025.11229335 Traballo presentado en: 2025 International Joint Conference on Neural Networks (IJCNN), Rome, Italy, 30 June - 05 July 2025, [Abstract]: Essential tremor (ET) is a prevalent movement disorder characterized by motor and non-motor symptoms, often associated with neurodegeneration. Optical coherence tomography (OCT) has emerged as a valuable tool to identify retinal biomarkers in ET patients. This study presents a novel methodology for ET detection using 3D point clouds derived from retinal OCT layers. Leveraging advanced geometric deep learning (GDL) architectures, including PointTransformer, PointCNN, PointNet++ and SplineCNN, we evaluated the diagnostic potential of individual retinal layers, including the Retinal Nerve Fiber Layer (RNFL), Ganglion Cell Layer (GCL) and Bruch’s Membrane (BM), as well as their combined representation. Our approach achieved state-of-the-art results, with PointTransformer obtaining an F1-score of 0.85 using only BM retinal surface, while requiring just 2% of the original point cloud size. These findings underscore the diagnostic value of OCT-derived 3D data and demonstrate the potential of GDL for computational biomarker extraction in neurodegenerative disorders, offering a scalable and efficient framework for ET diagnosis., This work was supported by the Instituto de Salud Carlos III (ISCIII), Government of Spain [grant numbers PI17/01726, PI20/00437, PI23/00935, RD21/0002/0050 (Inflammatory Disease Network - RICORS), FORT23/00010 (Programa FORTALECE)], the Ministerio de Ciencia e Innovacion, Government of Spain [grant numbers PID2023-148913OB-I00, TED2021-131201B-I00, and PDC2022-133132-I00], the Consellería de Educacion, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva [grant number ED431C 2024/33] and by the Government of Aragon [group B2323R]. This work was also supported by the Horizon Europe Programme through the ACHILLES/101189689 project (HORIZON-CL4-2024-DATA-01-01)., Xunta de Galicia; ED431C 2024/33
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

3D Features Fusion for Automated Segmentation of Fluid Regions in CSCR Patients: An OCT-based Photodynamic Therapy Response Analysis

  • Goyanes, Elena
  • Moura, Joaquim de
  • Fernández-Vigo, José Ignacio
  • García-Feijóo, Julián
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: Central Serous Chorioretinopathy (CSCR) is a significant cause of vision impairment worldwide, with Photodynamic Therapy (PDT) emerging as a promising treatment strategy. The capability to precisely segment fluid regions in Optical Coherence Tomography (OCT) scans and predict the response to PDT treatment can substantially augment patient outcomes. This paper introduces a novel deep learning (DL) methodology for automated 3D segmentation of fluid regions in OCT scans, followed by a subsequent PDT response analysis for CSCR patients. Our approach utilizes the rich 3D contextual information from OCT scans to train a model that accurately delineates fluid regions. This model not only substantially reduces the time and effort required for segmentation but also offers a standardized technique, fostering further large-scale research studies. Additionally, by incorporating pre- and post-treatment OCT scans, our model is capable of predicting PDT response, hence enabling the formulation of personalized treatment strategies and optimized patient management. To validate our approach, we employed a robust dataset comprising 2,769 OCT scans (124 3D volumes), and the results obtained were significantly satisfactory, outperforming the current state-of-the-art methods. This research signifies an important milestone in the integration of DL advancements with practical clinical applications, propelling us a step closer towards improved management of CSCR. Furthermore, the methodologies and systems developed can be adapted and extrapolated to tackle similar challenges in the diagnosis and treatment of other retinal pathologies, favoring more comprehensive and personalized patient care., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This work was supported by Ministerio de Ciencia e Innovación, Government of Spain through the research project with [grant numbers PID2019-108435RB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educación, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [grant number ED431C 2020/24], predoctoral grant [grant number ED481A-2023-152]. Furthermore, this work was supported by the Instituto de Salud Carlos III (ISCIII) under the grant [FORT23/00010] as part of the Programa FORTALECE del Ministerio de Ciencia e Innovación. Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED481A-2023-152
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

3D Point Cloud Analysis via Transformer-Based Graph Learning for Multiple Sclerosis Screening in OCT Images

  • Álvarez-Rodríguez, Lorena
  • García Prego, Iván
  • Moura, Joaquim de
  • Pueyo-Bestué, Ana
  • Viladés, Elisa
  • García-Martín, Elena
  • Sánchez, Clara I.
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
Presented at: 28th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2024), [Abstract]: Multiple Sclerosis (MS), the leading cause of non-traumatic neurological impairment in young adults, manifests morphological changes in the retina observable in Optical Coherence Tomography (OCT) images. These changes in the Retinal Nerve Fibre Layer (RNFL) and the Ganglion Cell Layer - Bruch’s Membrane (GCL-BM) serve as potential computational biomarkers for MS. In this work, we propose a transformer-based graph learning approach for analyzing 3D point clouds generated from RNFL and GCL-BM contours, marking a first in the application of geometric deep learning (GDL) to MS diagnosis via OCT scans. Our proposal, tailored for efficiency, synergizes the global contextual strengths of transformers with the detailed, structure-aware capabilities of graph neural networks. Such integration allows for the nuanced analysis of complex retinal structures, significantly boosting the precision of MS detection by uncovering patterns not discernible to the human eye. Additionally, we conducted a comprehensive study on the optimal downsampling size of input 3D point clouds, ensuring efficient data processing without compromising diagnostic accuracy. Our optimal configuration achieved a test F1-Score of 0.88, using only 4.0% of total 3D points, showcasing the effectiveness of our method despite the higher computational demands compared to less complex, albeit less precise, configurations. These promising results are the first in the study of 3D analysis and transformer-based geometric deep learning for MS screening based on OCT images, which are revolutionizing neurophtalmological research., Funded by Instituto de Salud Carlos III (ISCIII), Government of Spain, [projects PI17/01726 and PI20/00437]; Inflammatory Disease Network (RICORS) [project RD21/0002/0050]; Ministerio de Ciencia e Innovacion, Government of Spain [ projects PID2019-108435RB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educacion, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [grant number ED431C 2020/24]. Also supported by the ISCIII under the grant [FORT23/00010] as part of the Programa FORTALECE of Ministerio de Ciencia e Innovacion., Xunta de Galicia; ED431C 2020/24
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Detecting, Characterizing and Visualizing Multiple Sclerosis in Optical Coherence Tomography Through Biomarker Selection

  • López-Varela, Emilio
  • Barreira, Noelia
  • Olivier Pascual, Nuria
  • Quezada-Sánchez, Johnny
  • Oreja-Guevara, Celia
  • Rouco, José
[Abstract]: Multiple sclerosis (MS) is a chronic neurodegenerative disease affecting the central nervous system, which is the primary cause of non-traumatic neurological disability among young adults. Diagnosing MS is challenging yet crucial for effective patient treatment. Optical Coherence Tomography (OCT) has emerged as a non-invasive and efficient tool for analysing optic nerv alterations and assessing neurodegeneration in MS, particularly through changes in retinal thickness of layers such as the retinal nerve fiber layer (RNFL) and ganglion cell layer (GCL). In this work, we investigate the potential of using changes across all retinal layer thickness as a biomarker for MS detection. To accomplish this, we propose a fully automatic system consisting of an MS classification model and a pathological thickness visualization model. First, our system employs a fully convolutional neural network to segment retinal layers and choroidal vessels and to calculate the extraction of layer thickness at varying granularities. Global and local layer thickness are used as inputs for the MS classification model. A genetic multi objective algorithm is used for effective feature selection. Concurrently, voxel-level layer thickness serves as input for the visualization model that generates a 2D probability map where the pathological regions are highlighted. This map contributes to an interactive 3D reconstruction that provides a swift overview of MS-associated thickness changes. Extensive experimentation on real clinical MS cases validates the significant potential of the proposed system for practical clinical applications and showcases its efficacy in enhancing diagnostic precision and efficiency., This research was funded by Government of Spain, Ministerio de Ciencia e Innovación y Universidades, Government of Spain, RTI2018-095894-B-I00 research project; Ministerio de Ciencia e Innovación, Government of Spain through the research projects with reference PID2019-108435RB-I00, reference PDC2022-133132-I00 and TED2021-131201B-I00; Consellería de Cultura, Educación e Universidade, Xunta de Galicia through the Grupos de Referencia Competitiva, grant ref. ED431C 2020/24; CITIC, as Research Center accredited by Galician University System, is funded by “Consellería de Cultura, Educación e Universidade from Xunta de Galicia”, supported in an 80% through ERDF Funds, ERDF Operational Programme Galicia 2014–2020, and the remaining 20% by “Secretaría Xeral de Universidades”, grant ref. ED431G 2019/01. Emilio López Varela acknowledges its support under FPI Grant Program through PID2019-108435RB-I00 project., Xunta de Galicia; ED431G 2019/01, Xunta de Galicia; ED431C 2020/24
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Deep Learning-Based Approaches for Ciliary Muscle Segmentation and Biomarker Extraction

  • Goyanes, Elena
  • Moura, Joaquim de
  • Fernández-Vigo, José Ignacio
  • Fernández-Vigo, José A.
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
Presentado en: XX Conferencia de la Asociación Española para la Inteligencia Artificial, A Coruña, 19 - 21 de Junio de 2024 (CAEPIA 2024), [Abstract]: This paper highlights our recently published work that involves the application of deep learning techniques to perform the segmentation of the ciliary muscle in Anterior Segment Optical Coherence Tomography (AS-OCT) images. The ciliary muscle is vital for various anterior segment of the eye functions, including intraocular pressure regulation and lens shape maintenance. To advance research, we propose a fully automatic method for segmenting and measuring ciliary muscle biomarkers in 6 mm and 16 mm scan depths, commonly used in clinical analysis. Our approach ensures repeatable and immediate results through thorough exploration of artificial intelligence approaches combining different network architectures, encoders, data augmentation and transfer learning strategies. Additionally, we extract relevant biomarkers, aiding in diagnoses and monitoring of ocular diseases such as glaucoma, myopia, and presbyopia, and facilitating the development of new therapeutic strategies. With high accuracy values (0.9665 ± 0.1280 and 0.9772 ± 0.0873 for the best 6 mm and 16 mm combinations, respectively), our system provides clinicians and researchers with a valuable, automatic tool for ciliary muscle segmentation and analysis in AS-OCT images., This work was supported by Ministerio de Ciencia e Innovación, Government of Spain through the research project with [grant numbers RTI2018-095894-B-I00, PID2019-108435RB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educacioó, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, [grant number ED431C 2020/24], predoctoral grant [grant number ED481A-2023-152]., Xunta de Galicia; ED431C 2020/24, Xunta de Galicia; ED481A-2023-152
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Inter-expert reliability in multi-field-of-view automatic drusen segmentation analysis using optical coherence tomography

  • Goyanes, Elena
  • Leyva Santarén, Saúl
  • Herrero, Paula
  • Moura, Joaquim de
  • Novo Buján, Jorge
  • Ortega Hortas, Marcos
[Abstract]: Drusen are commonly associated with age-related macular degeneration (AMD), a leading cause of blindness in older adults. They can vary significantly in size, appearance, and location within the retina, impacting macular health in various ways. Smaller drusen may not affect the vision significantly, but larger and more numerous drusen can determine more severe AMD and a higher risk of progressing to late-stage disease, which can lead to significant visual impairment. Optical Coherence Tomography (OCT) is a critical imaging technique in the field of ophthalmology, particularly in the study and management of retinal diseases. The use of different fields of view (FoVs) in OCT imaging plays a pivotal role in enhancing our understanding and management of various retinal conditions, especially drusen. To address a crucial gap in the literature, this study introduces a novel fully-automatic approach for segmenting drusen in OCT images, applying FoV analysis for the first time to assist clinicians in diagnosing ocular diseases. To achieve this, we analyzed three different datasets, utilizing deep learning to enable a comprehensive comparison of segmentation accuracy across various FoVs and introducing a new method to assess inter-expert agreement in this challenging domain. Additionally, our research pioneers the segmentation of the 3×3mm area, essential for identifying significant retinal changes. Our approach not only closely aligns with expert assessments but also represents a significant step towards standardizing diagnostic procedures in ophthalmology, enhancing both the precision and efficiency of retinal image analysis to aid clinical decision-making., This work was supported by Ministerio de Ciencia e Innovación, Government of Spain through the research project with [grant numbers PID2023-148913OB-I00, TED2021-131201B-I00, and PDC2022-133132-I00]; Consellería de Educación, Universidade, e Formación Profesional, Xunta de Galicia, Grupos de Referencia Competitiva, Spain, [grant number ED431C 2024/33], predoctoral, Spain grant [grant number ED481A-2023-152]. Also supported by the ISCIII, Spain under the grant [FORT23/ 00010] as part of the Programa FORTALECE of Ministerio de Ciencia e Innovación. Also supported by the CNPq/MCTI/FNDCT [grant Number: 444625/2024-0]. Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431C 2024/33, Xunta de Galicia; ED481A-2023-152, Brasil. Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq); 444625/2024-0, Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Automatic segmentation of retinal layers in multiple neurodegenerative disorder scenarios

  • Gende, Mateo
  • Mallen, Víctor
  • de Moura, Joaquim
  • Cordón, Beatriz
  • Garcia-Martin, Elena
  • Sánchez, Clara I.
  • Novo, Jorge
  • Ortega, Marcos
Retinal Optical Coherence Tomography (OCT) allows the non-invasive direct observation of the central nervous system, enabling the measurement and extraction of biomarkers from neural tissue that can be helpful in the assessment of ocular, systemic and Neurological Disorders (ND). Deep learning models can be trained to segment the retinal layers for biomarker extraction. However, the onset of ND can have an impact on the neural tissue, which can lead to the degraded performance of models not exposed to images displaying signs of disease during training. We present a fully automatic approach for the retinal layer segmentation in multiple neurodegenerative disorder scenarios, using an annotated dataset of patients of the most prevalent NDs: Alzheimer's disease, Parkinson's disease, multiple sclerosis and essential tremor, along with healthy control patients. Furthermore, we present a two-part, comprehensive study on the effects of ND on the performance of these models. The results show that images of healthy patients may not be sufficient for the robust training of automated segmentation models intended for the analysis of ND patients, and that using images representative of different NDs can increase the model performance. These results indicate that the presence or absence of patients of ND in datasets should be taken into account when training deep learning models for retinal layer segmentation, and that the proposed approach can provide a valuable tool for the robust and reliable diagnosis in multiple scenarios of ND.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Fully automatic deep convolutional approaches for the screening of neurodegeneratives diseases using multi-view OCT images

  • Álvarez-Rodríguez, Lorena
  • Pueyo, Ana
  • de Moura, Joaquim
  • Vilades, Elisa
  • Garcia-Martin, Elena
  • Sánchez, Clara I.
  • Novo, Jorge
  • Ortega, Marcos
The prevalence of neurodegenerative diseases (NDDs) such as Alzheimer’s (AD), Parkinson’s (PD), Essential tremor (ET), and Multiple Sclerosis (MS) is increasing alongside the aging population. Recent studies suggest that these disorders can be identified through retinal imaging, allowing for early detection and monitoring via Optical Coherence Tomography (OCT) scans. This study is at the forefront of research, pioneering the application of multi-view OCT and 3D information to the neurological diseases domain. Our methodology consists of two main steps. In the first one, we focus on the segmentation of the retinal nerve fiber layer (RNFL) and a class layer grouping between the ganglion cell layer and Bruch’s membrane (GCL-BM) in both macular and optic disc OCT scans. These are the areas where changes in thickness serve as a potential indicator of NDDs. The second phase is to select patients based on information about the retinal layers. We explore how the integration of both views (macula and optic disc) improves each screening scenario: Healthy Controls (HC) vs. NDD, AD vs. NDD, ET vs. NDD, MS vs. NDD, PD vs. NDD, and a final multi-class approach considering all four NDDs. For the segmentation task, we obtained satisfactory results for both 2D and 3D approaches in macular segmentation, in which 3D performed better due to the inclusion of depth and cross-sectional information. As for the optic disc view, transfer learning did not improve the metrics over training from scratch, but it did provide a faster training. As for screening, 3D computational biomarkers provided better results than 2D ones, and multi-view methods were usually better than the single-view ones. Regarding separability among diseases, MS and PD were the ones that provided better results in their screening approaches, being also the most represented classes. In conclusion, our methodology has been successfully validated with an extensive experimentation of configurations, techniques and OCT views, becoming the first multi-view analysis that merges data from both macula-centered and optic disc-centered perspectives. Besides, it is also the first effort to examine key retinal layers across four major NDDs within the framework of pathological screening.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Contribución de congreso (ConferenceOutput)

Geometric Deep Learning for Essential Tremor Screening Using OCT-Derived 3D Point Clouds

  • Álvarez-Rodríguez, Lorena
  • de Moura, Joaquim
  • Vilades, Elisa
  • Garcia-Martin, Elena
  • Novo, Jorge
  • Ortega, Marcos
Essential tremor (ET) is a prevalent movement disorder characterized by motor and non-motor symptoms, often associated with neurodegeneration. Optical coherence tomography (OCT) has emerged as a valuable tool to identify retinal biomarkers in ET patients. This study presents a novel methodology for ET detection using 3D point clouds derived from retinal OCT layers. Leveraging advanced geometric deep learning (GDL) architectures, including PointTransformer, PointCNN, PointNet++ and SplineCNN, we evaluated the diagnostic potential of individual retinal layers, including the Retinal Nerve Fiber Layer (RNFL), Ganglion Cell Layer (GCL) and Bruch’s Membrane (BM), as well as their combined representation. Our approach achieved state-of-the-art results, with PointTransformer obtaining an F1-score of 0.85 using only BM retinal surface, while requiring just 2% of the original point cloud size. These findings underscore the diagnostic value of OCT-derived 3D data and demonstrate the potential of GDL for computational biomarker extraction in neurodegenerative disorders, offering a scalable and efficient framework for ET diagnosis.