Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 10
Encontrada(s) 1 página(s)

Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

New Method of Early RRMS Diagnosis Using OCT-Assessed Structural Retinal Data and Explainable Artificial Intelligence

  • Ortiz, Miguel
  • Pueyo, Ana
  • Dongil, Francisco J.
  • Boquete, Luciano
  • Sánchez-Morla, Eva M.
  • Barea, Rafael
  • Miguel-Jimenez, Juan M.
  • López-Dorado, Almudena
  • Vilades, Elisa
  • Rodrigo, María J.
  • Cordon, Beatriz
  • Garcia-Martin, Elena
Purpose: The purpose of this study was to provide the development of a method to classify optical coherence tomography (OCT)-assessed retinal data in the context of automatic diagnosis of early-stage multiple sclerosis (MS) with decision explanation. Methods: The database used contains recordings from 79 patients with recently diagnosed relapsing-remitting multiple sclerosis (RRMS) and no history of optic neuritis and from 69 age-matched healthy control subjects. Analysis was performed on the thicknesses (average right and left eye value and inter-eye difference) of the macular retinal nerve fiber layer (mRNFL), macular ganglion cell layer (mGCL), macular inner plexiform layer (mIPL), and macular inner retinal complex layer (mIRL), dividing the macular area into six analysis zones. Recursive feature extraction (RFE) and Shapley additive explanations (SHAP) are combined to rank relevant features and select the subset that maximizes classifier (support vector machine [SVM]) performance. Results: Of the initial 48 features, 20 were identified as maximizing classifier accuracy (n = 0.9257). The SHAP values indicate that average thickness has greater relevance than inter-eye difference, that the mGCL and mRNFL are the most influential structures, and that the peripheral papillomacular bundle and the supero-temporal quadrant are the zones most affected. Conclusions: This approach improves the success rate of automatic diagnosis of early-stage RRMS and enhances clinical decision making transparency.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Addressing cross-population domain shift in chest X-ray classification through supervised adversarial domain adaptation

  • Musa, Aminu
  • Prasad, Rajesh
  • Hernández, Mónica
Medical image analysis, empowered by artificial intelligence (AI), plays a crucial role in modern healthcare diagnostics. However, the effectiveness of machine learning models hinges on their ability to generalize to diverse patient populations, presenting domain shift challenges. This study explores the domain shift problem in chest X-ray classification, focusing on cross-population variations, especially in underrepresented groups. We analyze the impact of domain shifts across three population datasets acting as sources using a Nigerian chest X-ray dataset acting as the target. Model performance is evaluated to assess disparities between source and target populations, revealing large discrepancies when the models trained on a source were applied to the target domain. To address with the evident domain shift among the populations, we propose a supervised adversarial domain adaptation (ADA) technique. The feature extractor is first trained on the source domain using a supervised loss function in ADA. The feature extractor is then frozen, and an adversarial domain discriminator is introduced to distinguish between the source and target domains. Adversarial training fine-tunes the feature extractor, making features from both domains indistinguishable, thereby creating domain-invariant features. The technique was evaluated on the Nigerian dataset, showing significant improvements in chest X-ray classification performance. The proposed model achieved a 90.08% accuracy and a 96% AUC score, outperforming existing approaches such as multi-task learning (MTL) and continual learning (CL). This research highlights the importance of developing domain-aware models in AI-driven healthcare, offering a solution to cross-population domain shift challenges in medical imaging.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Otros (Other)

Actualización de la utilidad de la angiografía mediada por tomografía de coherencia óptica en las enfermedades neurodegenerativas

Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

A Superpixel-Based Algorithm for Detecting Optical Density Changes in Choroidal Optical Coherence Tomography Images of Diabetic Patients

  • Otin, Sofia
  • Mallen-Gracia, Victor
  • Perez-Maña, Luis
  • Ávila, Francisco J.
  • Garcia-Martin, Elena
This study explored the diagnostic potential of image-processing analysis in optical coherence tomography (OCT) images to detect systemic vascular changes in individuals with systemic diseases. Methods: Ocular OCT images from two cohorts diabetic patients and healthy control subjects were analyzed. A novel Superpixel Segmentation (SpS) algorithm was used to process these images and extract optical image density information from ocular vascular tissue. The algorithm was applied to isolate the choroid layer for analysis of its optical properties. The procedure was performed by separate examiners, and both inter- and intra-observer repeatability were assessed. Choroidal area (CA) and choroidal optical image density (COID) metrics were used to assess structural changes in the vascular tissue and predict alterations in the choroidal parameters. Results: A total of 110 diabetic patient eye images and 92 healthy control images were processed. The results showed significant differences in CA and COID between diabetic and healthy eyes, indicating that these parameters could serve as valuable biomarkers for early vascular damage. Conclusions: The use of the SpS algorithm on OCT B-scan images allows for the identification of new parameters linked to ocular vascular damage. These findings suggest that digital image-processing techniques can reveal differences in vascular tissue, offering potential new indicators of pathology.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

A Systematic Review of Cross-Population Shifts in Medical Imaging Analysis with Deep Learning

  • Musa, Aminu
  • Prasad, Rajesh
  • Onwualu, Peter
  • Hernández, Mónica
Deep learning has achieved expert-level performance in medical imaging analysis. However, models often fail to generalize across patient populations due to cross-population domain shifts, distributional differences arising from demographic variability, variations in imaging protocols, scanner hardware, and differences in disease prevalence. This challenge limits the real-world deployment and can increase health inequities. This review systematically examines the nature, causes, and impact of cross-population domain shift in deep learning-based medical imaging analysis. We analyzed 50 peer-reviewed studies from 2020 to 2025, evaluating the proposed methodologies for handling population shifts, the datasets employed, and the metrics used to assess performance. Our findings demonstrate that performance degradation ranged from 10–25% when models were tested on unseen populations, emphasizing the substantial impact of domain shifts on model generalizability. The literature reveals that mitigation strategies broadly fall into two categories: data-centric approaches, such as augmentation and harmonization, and model-centric approaches, including domain adaptation, transfer learning, adversarial learning, multi-task learning, and continual learning. While domain adaptation and transfer learning are the most widely used, their performance gains across populations remain modest, ranging from 5–15%, and are not supported by external validation. Our synthesis reveals a significant reliance on large, publicly available datasets from limited regions, with an underrepresentation of data from low- and middle-income countries. Evaluation practices are inconsistent, with few studies employing standardized external test sets. This review provides a structured taxonomy of mitigation techniques, a refined analysis of domain shift characteristics, and an in-depth critique of methodological challenges. We highlight the urgent need for more geographically and demographically inclusive datasets, adaptable modeling techniques, and standardized evaluation protocols to enable accurate and equitable AI-driven diagnostics across diverse populations. Finally, we outline future research directions to guide the development of robust, generalizable, and fair models for medical imaging analysis. El aprendizaje profundo ha alcanzado un rendimiento de nivel experto en el análisis de imágenes médicas. Sin embargo, los modelos a menudo no logran generalizar entre poblaciones de pacientes debido a cambios de dominio entre poblaciones, diferencias de distribución derivadas de la variabilidad demográfica, variaciones en los protocolos de imagen, el hardware del escáner y diferencias en la prevalencia de enfermedades. Este desafío limita la implementación en el mundo real y puede aumentar las inequidades en salud. Esta revisión examina sistemáticamente la naturaleza, las causas y el impacto de los cambios de dominio entre poblaciones en el análisis de imágenes médicas basado en aprendizaje profundo. Analizamos 50 estudios revisados ​​por pares de 2020 a 2025, evaluando las metodologías propuestas para manejar los cambios de población, los conjuntos de datos empleados y las métricas utilizadas para evaluar el rendimiento. Nuestros hallazgos demuestran que la degradación del rendimiento osciló entre el 10 % y el 25 % cuando los modelos se probaron en poblaciones no vistas, lo que enfatiza el impacto sustancial de los cambios de dominio en la generalización del modelo. La literatura revela que las estrategias de mitigación se dividen en dos categorías principales: enfoques centrados en datos, como la ampliación y la armonización, y enfoques centrados en modelos, que incluyen la adaptación de dominio, el aprendizaje por transferencia, el aprendizaje adversario, el aprendizaje multitarea y el aprendizaje continuo. Si bien la adaptación de dominio y el aprendizaje por transferencia son los más utilizados, sus mejoras de rendimiento en diferentes poblaciones siguen siendo modestas, oscilando entre el 5 % y el 15 %, y carecen de validación externa. Nuestra síntesis revela una dependencia significativa de grandes conjuntos de datos públicos procedentes de regiones limitadas, con una escasa representación de datos de países de ingresos bajos y medios. Las prácticas de evaluación son inconsistentes, y pocos estudios emplean conjuntos de prueba externos estandarizados. Esta revisión proporciona una taxonomía estructurada de las técnicas de mitigación, un análisis refinado de las características del cambio de dominio y una crítica exhaustiva de los desafíos metodológicos. Destacamos la necesidad urgente de contar con conjuntos de datos más inclusivos desde el punto de vista geográfico y demográfico, técnicas de modelado adaptables y protocolos de evaluación estandarizados para permitir diagnósticos precisos y equitativos basados ​​en IA en diversas poblaciones. Por último, describimos las futuras líneas de investigación para guiar el desarrollo de modelos robustos, generalizables y justos para el análisis de imágenes médicas.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Clues to prognosis in anterior ischemic optic neuropathy: an optical coherence tomography angiography study

  • Rodrigo, Maria J.
  • Pérez-Gómez, Pablo
  • Fuertes, Isabel
  • Pablo, Luis E.
  • Subías, Manuel
  • Casanovas-Marsal, Josep O.
  • Garcia-Martin, Elena
AIM: To investigate optic nerve vascularization in patients with anterior ischemic optic neuropathy (AION) during the first 3mo after onset, using comprehensive ophthalmic assessments combined with optical coherence tomography (OCT) and optical coherence tomography angiography (OCT-A). METHODS: A prospective longitudinal observational study was performed with a 3-month follow-up. Clinical data recorded included age, sex, laterality of ocular involvement, AION subtype, previous history of ischemic events, cardiovascular risk factors such as high blood pressure, dyslipidemia, diabetes mellitus, smoking status, obstructive sleep apnea, and systemic treatments received. Functional, structural, and vascular examinations, including best corrected visual acuity (BCVA), visual field, OCT, and OCT-A, were performed at baseline, 1, and 3mo. RESULTS: Twenty-two subjects included 12 patients with AION and 10 healthy controls were enrolled. Mean age was 63.75±8.32y in the AION group and 61.80±5.04y in the control group (P=0.365). Gender and laterality distributions were comparable. AION patients showed significantly decreased optic nerve head perfusion at baseline (P=0.024) and 1mo (P=0.033). OCT revealed early thickening and subsequent atrophy of the peripapillary retinal nerve fiber layer and macular layers. OCT-A vascular parameters correlated significantly with 1-month BCVA (r=0.800, P≤0.05) and 3-month structural outcomes (r=0.807-0.835, P≤0.05). CONCLUSION: Vascular parameters derived from OCT-A can act as predictive markers for medium-term visual and structural outcomes in patients with ischemic optic neuropathy.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Neuroretinal damage associated with pituitary macroadenoma: endocrine and radiological predictors and correlation with optical coherence tomography-derived biomarkers

  • Fernandez-Velasco, Diego
  • Garcia-Martin, Elena
  • Santamaria, Belen
  • Rodrigo, María Jesús
Objective: To identify endocrine and radiological tumor characteristics associated with higher risk of visual impairment. Methods: A retrospective observational study included 40 patients with pituitary macroadenoma. Variables analyzed were age, sex, disease duration, treatment, hormonal profile, tumor volume, and ophthalmic parameters: visual acuity (VA), perimetry, and retinal analysis using optical coherence tomography (OCT). Results: Surgery normalized ACTH, cortisol, IGF-1, and prolactin levels. Larger tumor volumes were observed in males, nonfunctioning tumors, nonoperated patients, and relapses. Larger tumors were associated with worse visual field, while VA remained stable. OCT showed thinning of total retina and inner retinal layers in patients with disease duration >5 years, nonfunctioning tumors, larger tumors, postoperative status, and relapse (p < 0.05). Macular ganglion cell layer thickness correlated inversely with IGF-1 and prolactin, and retinal nerve fiber layer with tumor size. The inner nuclear layer exhibited a non-linear behavior, thickening in early stages while thinning in severe injury. Conclusion: Hormonal and radiological factors are associated with visual dysfunction. OCT and perimetry detect early visual pathway damage better than VA. Non-linear behavior of the INL stand out as a potential prognostic biomarker.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

3D OCT-Based Retinal Biomarker Analysis for Automatic Regional-Wise Characterization of Neurodegenerative Diseases

  • Álvarez-Rodríguez, Lorena
  • Vázquez, Carlota
  • Cordón, Beatriz
  • Garcia-Martin, Elena
  • de Moura, Joaquim
  • Novo, Jorge
  • Ortega, Marcos
Neurodegenerative diseases (NDDs) such as Alzheimer’s disease (AD), essential tremor (ET), multiple sclerosis (MS), and Parkinson’s disease (PD) are complex disorders that often exhibit overlapping symptoms, leading to diagnostic challenges. Given the increasing interest in retinal imaging as a non-invasive biomarker for neurodegeneration, this study proposes a fully automated machine learning pipeline for disease characterization using optical coherence tomography (OCT). We analyze macular thickness patterns across three key and relevant retinal elements: retinal nerve fibre layer (RNFL), ganglion cell layer to Bruch’s membrane (GCL-BM), and the total retina. These are processed by two complementary regional layouts: the standard ETDRS scheme and a custom 33 quadrant grid. These measurements are used to train multiple classifiers to distinguish between healthy controls and NDDs either collectively or individually. The proposed method processes 34,375 OCT B-scans from 353 subjects and highlights disease-specific thickness patterns with a pathological distinction score ranging up to 0.71 depending on the retinal region, disease, and classifier. Sector-based grids generally outperform quadrant-based ones, revealing highly localized pathological signatures. Our findings demonstrate that each disease manifests distinct retinal alterations, aligning with current clinical literature while offering novel insights for ET and PD. The study reinforces the potential of grid-based OCT analysis as a discriminative and fully automatic screening tool, paving the way for improved early diagnosis and differential analysis of NDDs through retinal biomarkers.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Neuroretinal Alterations in Persistent COVID-19: A Two-Year OCT Follow-Up

  • Artiaga, Naiara
  • Vilades, Elisa
  • Cordón, Beatriz
  • Satue, María
  • Fanlo-Zarazaga, Alvaro
  • Fernández-Velasco, Diego
  • García-Martín, Elena
Background/Objectives: To evaluate long-term neuroretinal changes in patients with persistent COVID-19 (PC) versus asymptomatic controls, using optical coherence tomography (OCT) over a two-year follow-up. Methods: This prospective longitudinal study enrolled 133 participants: 94 PC patients and 39 control subjects. Participants underwent comprehensive ophthalmological assessment at baseline, at 1 year (voluntary), and at 2 years. Structural retinal changes were analysed using spectral-domain OCT with the Bruch’s Membrane Opening–Minimum Rim Width and Posterior Pole protocols. Longitudinal analyses focused on within-subject change from baseline to 2 years and on between-group comparisons of these change scores, with Bonferroni correction applied within predefined families of comparisons. Results: The most robust corrected between-group longitudinal finding was a greater decrease in the central macular sector (C0) of the inner plexiform layer (IPL) in PC patients than in control subjects. Conclusions: Although these findings suggest possible subtle inner retinal involvement in PC patients, particularly in the central IPL, the results should be interpreted cautiously because of the modest control sample, control-group heterogeneity, and the exploratory nature of the sectoral OCT analyses. OCT may be useful in research settings as a complementary tool for exploring subtle neuroretinal changes in PC patients; however, its clinical utility and role as a validated biomarker remain unproven.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

AI-Based Classification of Multiple Sclerosis Using OCT Retinal Layer Thickness Across Two Centers

  • Ortiz, Miguel
  • Dongil-Moreno, Javier
  • Rebolleda, Gema
  • Artiaga, Naiara
  • Boquete, Luciano
  • Miguel-Jimenez, Juan M.
  • Rodrigo, Maria J.
  • López-Dorado, Almudena
  • Zamora, Rosario
  • García Vicente, Eduardo
  • Sánchez-Morla, Eva M.
  • Andres-Luna, Beatriz
  • Muñoz Negrete, Francisco J.
  • Garcia-Martin, Elena
Background: The latest revision of the McDonald criteria for diagnosis of multiple sclerosis (MS) establishes that the optic nerve can serve as a fifth anatomical location within the central nervous system for diagnosis. Optical coherence tomography (OCT) images can serve as evidence for this purpose. Objective: To assess the accuracy of automated artificial-intelligence-based classification of MS patients using OCT data obtained from two different centers. Methods: OCT data were collected from two centers using standardized APOSTEL-based protocols and similar equipment. Retinal layer thicknesses—mean and standard deviation (STD) values—were analyzed in four layers and in six regions per layer per eye. A support vector machine classifier with recursive feature elimination and Shapley additive explanations value analysis was applied to identify the most relevant features and maximize classification accuracy between control subject and MS patient eyes. Results: The database drawn from two hospitals comprised 112 eyes with MS without prior history of optic neuritis and 193 eyes of control subjects. The classifier achieved maximum accuracy (0.8459) using 20 input features. The mean and STD metrics had similar importance, with the most influential layers being the ganglion cell layer, inner plexiform layer, and the inner retinal layer complex. Key regions included the papillomacular bundle and the superior temporal perimacular area. Conclusions: OCT data facilitates highly accurate MS diagnosis across different centers. Artificial intelligence assessment could facilitate automated classification. These findings provide evidence of the important role of the optic nerve in MS diagnosis.