Pasar al contenido principal

SISTEMA DE INTERPRETACION DE IMAGENES HISTOPATOLOGICAS PARA LA DETECCION DE CANCER DE PROSTATA

DPI2016-77869-C2-1-R

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2016
Plan Estatal 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSITAT POLITÈCNICA DE VALÈNCIA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 16
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Automatic Segmentation of Epidermis and Hair Follicles in Optical Coherence Tomography Images of Normal Skin by Convolutional Neural Networks

  • del Amor, Rocío
  • Morales, Sandra|||0000-0003-0763-1545
  • Colomer, Adrián|||0000-0002-7616-6029
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
  • Mogensen, Mette
  • Jensen, Mikkel
  • Israelsen, Niels M.
  • Bang, Ole
[EN] Optical coherence tomography (OCT) is a well-established bedside imaging modality that allows analysis of skin structures in a non-invasive way. Automated OCT analysis of skin layers is of great relevance to study dermatological diseases. In this paper, an approach to detect the epidermal layer along with the follicular structures in healthy human OCT images is presented. To the best of the authors' knowledge, the approach presented in this paper is the only epidermis detection algorithm that segments the pilosebaceous unit, which is of importance in the progression of several skin disorders such as folliculitis, acne, lupus erythematosus, and basal cell carcinoma. The proposed approach is composed of two main stages. The first stage is a Convolutional Neural Network based on U-Net architecture. The second stage is a robust post-processing composed by a Savitzky-Golay filter and Fourier Domain Filtering to fully define the borders belonging to the hair follicles. After validation, an average Dice of 0.83 +/- 0.06 and a thickness error of 10.25 mu mis obtained on 270 human skin OCT images. Based on these results, the proposed method outperforms other state-of-the-art methods for epidermis segmentation. It demonstrates that the proposed image segmentation method successfully detects the epidermal region in a fully automatic way in addition to defining the follicular skin structures as main novelty., This work has been partially supported by Horizon 2020, the European Union's Framework Programme for Research and Innovation, under grant agreement No. 732613 (GALAHAD Project), the Spanish Ministry of Economy and Competitiveness through project DPI2016-77869, and GVA through project PROMETEO/2019/109. The OCT system and the work of NI were funded by Innovation Fund Denmark, Grant No. 4107-00011A (ShapeOCT).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

A Deep Embedded Framework for Spitzoid Neoplasm Classification Using DNA Methylation Data

  • del Amor, Rocío
  • Colomer, Adrián|||0000-0002-7616-6029
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
  • Monteagudo, Carlos
  • Garzón, María José
  • García-Giménez, José Luis
[EN] Spitzoid melanocytic tumors (SMT) are a group of neoplasms that represent a formidable diagnostic challenge for dermatopathologists. DNA methylation (DNAm) is a welldefined epigenetic factor that has an important role in the development of these lesions. In this work, we propose different deep-learning-based approaches to address the Spitzoid neoplasms detection from DNAm. We use an autoencoder and a variational autoencoder for dimensionality reduction with a subsequently supervised classification. Additionally, we present a deep embedded refined clustering algorithm able to optimize the latent space at the same time that the non-supervised classification task is performed. This novel approach in DNAm supposes a step forward in the SMT detection as suggest the obtained results (acc = 0.9). Additionally, making use of the resulting model, we present a subspace-prototypical-based approach for the prognostic prediction of uncertain malignant potential samples, which is nowadays the hottest open area in SMT detection., This work has received funding from Horizon 2020, the European Union¿s Framework Programme for Research and Innovation, under grant agreement No. 860627 (CLARIFY), the Spanish Ministry of Economy and Competitiveness through project PID2019-105142RB-C21 (AI4SKIN) and SICAP (DPI2016-77869-C2-1-R) and GVA through project PROMETEO/2019/109
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Gleason Grading of Histology Prostate Images through Semantic Segmentation via Residual U-Net

  • Kalapahar, Amartya
  • Silva-Rodríguez, Julio José
  • Colomer, Adrián|||0000-0002-7616-6029
  • López-Mir, Fernando|||0000-0001-8286-6796
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
[EN] Worldwide, prostate cancer is one of the main cancers affecting men. The final diagnosis of prostate cancer is based on the visual detection of Gleason patterns in prostate biopsy by pathologists. Computer-aided-diagnosis systems allow to delineate and classify the cancerous patterns in the tissue via computer-vision algorithms in order to support the physicians¿ task. The methodological core of this work is a U-Net convolutional neural network for image segmentation modified with residual blocks able to segment cancerous tissue according to the full Gleason system. This model outperforms other well-known architectures, and reaches a pixel-level Cohen¿s quadratic Kappa of 0.52, at the level of previous image-level works in the literature, but providing also a detailed localisation of the patterns., This work was supported by the Spanish Ministry of Economy and Competitiveness through project DPI2016-77869. The work of Fernando Lopez-Mir has been supported by the Polytechnic University of Valencia (Grant PAID-10-18). The Titan V used for this research was donated by the NVIDIA Corporation.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Circumpapillary OCT-Focused Hybrid Learning for Glaucoma Grading Using Tailored Prototypical Neural Networks

  • García-Pardo, José Gabriel
  • Verdú-Monedero, Rafael
  • Morales-Sanchez, Juan
  • del Amor, Rocío
  • Colomer, Adrián|||0000-0002-7616-6029
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
[EN] Glaucoma is one of the leading causes of blindness worldwide and Optical Coherence Tomography (OCT) is the quintessential imaging technique for its detection. Unlike most of the state-of-the-art studies focused on glaucoma detection, in this paper, we propose, for the first time, a novel framework for glaucoma grading using raw circumpapillary B-scans. In particular, we set out a new OCT-based hybrid network which combines hand-driven and deep learning algorithms. An OCT-specific descriptor is proposed to extract hand-crafted features related to the retinal nerve fibre layer (RNFL). In parallel, an innovative CNN is developed using skip-connections to include tailored residual and attention modules to refine the automatic features of the latent space. The proposed architecture is used as a backbone to conduct a novel few-shot learning based on static and dynamic prototypical networks. The k-shot paradigm is redefined giving rise to a supervised end-to-end system which provides substantial improvements discriminating between healthy, early and advanced glaucoma samples. The training and evaluation processes of the dynamic prototypical network are addressed from two fused databases acquired via Heidelberg Spectralis system. Validation and testing results reach a categorical accuracy of 0.9459 and 0.8788 for glaucoma grading, respectively. Besides, the high performance reported by the proposed model for glaucoma detection deserves a special mention. The findings from the class activation maps are directly in line with the clinicians' opinion since the heatmaps pointed out the RNFL as the most relevant structure for glaucoma diagnosis., This work has been partially funded by the following projects: [H2020-ICT-2016-2017, 732613] , DPI2016-77869-C2-1-R, PROM-ETEO/2019/109, AES2017-PI17/00771, AES2017-PI17/00821 and 20901/PI/18. The work of Gabriel Garcia has been supported by the Spanish State Research Agency PTA2017-14610-I
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Glaucoma Detection from Raw SD-OCT Volumes: a Novel Approach Focused on Spatial Dependencies

  • García-Pardo, José Gabriel
  • Colomer, Adrián|||0000-0002-7616-6029
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
[EN] Background and objective:Glaucoma is the leading cause of blindness worldwide. Many studies based on fundus image and optical coherence tomography (OCT) imaging have been developed in the literature to help ophthalmologists through artificial-intelligence techniques. Currently, 3D spectral-domain optical coherence tomography (SD-OCT) samples have become more important since they could enclose promising information for glaucoma detection. To analyse the hidden knowledge of the 3D scans for glaucoma detection, we have proposed, for the first time, a deep-learning methodology based on leveraging the spatial dependencies of the features extracted from the B-scans. Methods:The experiments were performed on a database composed of 176 healthy and 144 glaucomatous SD-OCT volumes centred on the optic nerve head (ONH). The proposed methodology consists of two well-differentiated training stages: a slide-level feature extractor and a volume-based predictive model. The slide-level discriminator is characterised by two new, residual and attention, convolutional modules which are combined via skip-connections with other fine-tuned architectures. Regarding the second stage, we first carried out a data-volume conditioning before extracting the features from the slides of the SD-OCT volumes. Then, Long Short-Term Memory (LSTM) networks were used to combine the recurrent dependencies embedded in the latent space to provide a holistic feature vector, which was generated by the proposed sequential-weighting module (SWM). Results:The feature extractor reports AUC values higher than 0.93 both in the primary and external test sets. Otherwise, the proposed end-to-end system based on a combination of CNN and LSTM networks achieves an AUC of 0.8847 in the prediction stage, which outperforms other state-of-the-art approaches intended for glaucoma detection. Additionally, Class Activation Maps (CAMs) were computed to highlight the most interesting regions per B-scan when discerning between healthy and glaucomatous eyes from raw SD-OCT volumes. Conclusions:The proposed model is able to extract the features from the B-scans of the volumes and combine the information of the latent space to perform a volume-level glaucoma prediction. Our model, which combines residual and attention blocks with a sequential weighting module to refine the LSTM outputs, surpass the results achieved from current state-of-the-art methods focused on 3D deep-learning architectures., The authors gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan V GPU used here., This work has been funded by GALAHAD project [H2020-ICT-2016-2017, 732613], SICAP project (DPI2016-77869-C2-1-R) and GVA through project PROMETEO/2019/109. The work of Gabriel García has been supported by the State Research Spanish Agency PTA2017-14610-I.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Self-learning for weakly supervised Gleason grading of local patterns

  • Silva-Rodríguez, Julio
  • Dolz, Jose
  • Colomer, Adrián|||0000-0002-7616-6029
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
[EN] Prostate cancer is one of the main diseases affecting men worldwide. The gold standard for diagnosis and prognosis is the Gleason grading system. In this process, pathologists manually analyze prostate histology slides under microscope, in a high time-consuming and subjective task. In the last years, computer-aided-diagnosis (CAD) systems have emerged as a promising tool that could support pathologists in the daily clinical practice. Nevertheless, these systems are usually trained using tedious and prone-to-error pixel-level annotations of Gleason grades in the tissue. To alleviate the need of manual pixel-wise labeling, just a handful of works have been presented in the literature. Furthermore, despite the promising results achieved on global scoring the location of cancerous patterns in the tissue is only qualitatively addressed. These heatmaps of tumor regions, however, are crucial to the reliability of CAD systems as they provide explainability to the system's output and give confidence to pathologists that the model is focusing on medical relevant features. Motivated by this, we propose a novel weakly-supervised deeplearning model, based on self-learning CNNs, that leverages only the global Gleason score of gigapixel whole slide images during training to accurately perform both, grading of patch-level patterns and biopsy-level scoring. To evaluate the performance of the proposed method, we perform extensive experiments on three different external datasets for the patch-level Gleason grading, and on two different test sets for global Grade Group prediction. We empirically demonstrate that our approach outperforms its supervised counterpart on patch-level Gleason grading by a large margin, as well as state-of-the-art methods on global biopsylevel scoring. Particularly, the proposed model brings an average improvement on the Cohen's quadratic kappa (kappa) score of nearly 18% compared to full-supervision for the patch-level Gleason grading task. This suggests that the absence of the annotator's bias in our approach and the capability of using large weakly labeled datasets during training leads to higher performing and more robust models. Furthermore, raw features obtained from the patchlevel classifier showed to generalize better than previous approaches in the literature to the subjective global biopsylevel scoring., This work was supported by the Spanish Ministry of Economy and Competitiveness through Projects DPI2016-77869 and PID2019-105142RB-C21.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Detection of Early Signs of Diabetic Retinopathy Based on Textural and Morphological Information in Fundus Images

  • Colomer, Adrián|||0000-0002-7616-6029
  • Igual García, Jorge|||0000-0003-3408-4014
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
[EN] Estimated blind people in the world will exceed 40 million by 2025. To develop novel algorithms based on fundus image descriptors that allow the automatic classification of retinal tissue into healthy and pathological in early stages is necessary. In this paper, we focus on one of the most common pathologies in the current society: diabetic retinopathy. The proposed method avoids the necessity of lesion segmentation or candidate map generation before the classification stage. Local binary patterns and granulometric profiles are locally computed to extract texture and morphological information from retinal images. Different combinations of this information feed classification algorithms to optimally discriminate bright and dark lesions from healthy tissues. Through several experiments, the ability of the proposed system to identify diabetic retinopathy signs is validated using different public databases with a large degree of variability and without image exclusion., This work has been partially supported by the Spanish Ministry of Economy and Competitiveness through project DPI2016-77869 and GVA through project PROMETEO/2019/109
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Capítulo o parte de un libro (BookPart)

Identification of Individual Glandular Regions Using LCWT and Machine Learning Techniques

  • García-Pardo, José Gabriel
  • Peñaranda, Francisco
  • Sales, María Ángeles
  • Colomer, Adrián|||0000-0002-7616-6029
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
A new approach for the segmentation of gland units in histological images is proposed with the aim of contributing to the improvement of the prostate cancer diagnosis. Clustering methods on several colour spaces are applied to each sample in order to generate a binary mask of the different tissue components. From the mask of lumen candidates, the Locally Constrained Watershed Transform (LCWT) is applied as a novel gland segmentation technique never before used in this type of images. 500 random gland candidates, both benign and pathological, are selected to evaluate the LCWT technique providing results of Dice coefficient of 0.85. Several shape and textural descriptors in combination with contextual features and a fractal analysis are applied, in a novel way, on different colour spaces achieving a total of 297 features to discern between artefacts and true glands. The most relevant features are then selected by an exhaustive statistical analysis in terms of independence between variables and dependence with the class. 3.200 artefacts, 3.195 benign glands and 3.000 pathological glands are obtained, from a data set of 1468 images at 10x magnification. A careful strategy of data partition is implemented to robustly address the classification problem between artefacts and glands. Both linear and non-linear approaches are considered using machine learning techniques based on Support Vector Machines (SVM) and feedforward neural networks achieving values of sensitivity, specificity and accuracy of 0.92, 0.97 and 0.95, respectively, This work has been funded by the Ministry of Economy, Industry and Competitiveness under the SICAP project (DPI2016-77869-C2-1-R). The work of Adri´an Colomer has been supported by the Spanish FPI Grant BES-2014-067889. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A TV-based image processing framework for blind color deconvolution and classification of histological images

  • Pérez-Bueno, Fernando
  • López-Pérez, Miguel
  • Vega, Miguel
  • Mateos, Javier
  • Molina, Rafael
  • Katsaggelos, Aggelos K.
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
[EN] In digital histopathological image analysis, two conflicting objectives are often pursued: closeness to the original tissue and high classification performance. The former objective tries to recover images (stains) that are as close as possible to the ones obtained by staining the tissue with a single dye. The latter objective requires images that allow the extraction of better features for an improved classification, even if their appearance is not close to single stained tissues. In this paper we propose a framework that achieves both objectives depending on the number of stains used to mathematically decompose the scanned image. The proposed framework uses a total variation prior for each stain together with the similarity to a given reference color-vector matrix. Variational inference and an evidence lower bound are utilized to automatically estimate all the latent variables and model parameters. The proposed methodology is tested on real images and compared to classical and state-of-the-art methods for histopathological blind image color deconvolution and prostate cancer classification., This work was sponsored in part by Ministerio de Ciencia e Innovacion under Contract BES-2017-081584 and project DPI2016-77869-C2-2-R.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Going deeper through the Gleason scoring scale: An automatic end-to-end system for histology prostate grading and cribriform pattern detection

  • Silva-Rodríguez, Julio
  • Sales, María A.
  • Molina, Rafael
  • Colomer, Adrián|||0000-0002-7616-6029
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
[EN] Background and Objective: Prostate cancer is one of the most common diseases affecting men worldwide. The Gleason scoring system is the primary diagnostic and prognostic tool for prostate cancer. Further-more, recent reports indicate that the presence of patterns of the Gleason scale such as the cribriform pattern may also correlate with a worse prognosis compared to other patterns belonging to the Glea-son grade 4. Current clinical guidelines have indicated the convenience of highlight its presence during the analysis of biopsies. All these requirements suppose a great workload for the pathologist during the analysis of each sample, which is based on the pathologist's visual analysis of the morphology and or-ganisation of the glands in the tissue, a time-consuming and subjective task. In recent years, with the development of digitisation devices, the use of computer vision techniques for the analysis of biopsies has increased. However, to the best of the authors' knowledge, the development of algorithms to automatically detect individual cribriform patterns belonging to Gleason grade 4 has not yet been studied in the literature. The objective of the work presented in this paper is to develop a deep-learning-based system able to support pathologists in the daily analysis of prostate biopsies. This analysis must include the Gleason grading of local structures, the detection of cribriform patterns, and the Gleason scoring of the whole biopsy. Methods: The methodological core of this work is a patch-wise predictive model based on convolutional neural networks able to determine the presence of cancerous patterns based on the Gleason grading system. In particular, we train from scratch a simple self-design architecture with three filters and a top model with global-max pooling. The cribriform pattern is detected by retraining the set of filters of the last convolutional layer in the network. Subsequently, a biopsy-level prediction map is reconstructed by bi-linear interpolation of the patch-level prediction of the Gleason grades. In addition, from the re-constructed prediction map, we compute the percentage of each Gleason grade in the tissue to feed a multi-layer perceptron which provides a biopsy-level score. Results: In our SICAPv2 database, composed of 182 annotated whole slide images, we obtained a Cohen's quadratic kappa of 0.77 in the test set for the patch-level Gleason grading with the proposed architec-ture trained from scratch. Our results outperform previous ones reported in the literature. Furthermore, this model reaches the level of fine-tuned state-of-the-art architectures in a patient-based four groups cross validation. In the cribriform pattern detection task, we obtained an area under ROC curve of 0.82. Regarding the biopsy Gleason scoring, we achieved a quadratic Cohen's Kappa of 0.81 in the test subset. Shallow CNN architectures trained from scratch outperform current state-of-the-art methods for Gleason grades classification. Our proposed model is capable of characterising the different Gleason grades in prostate tissue by extracting low-level features through three basic blocks (i.e. convolutional layer + max pooling). The use of global-max pooling to reduce each activation map has shown to be a key factor for reducing complexity in the model and avoiding overfitting. Regarding the Gleason scoring of biopsies, a multi-layer perceptron has shown to better model the decision-making of pathologists than previous simpler models used in the literature., This work was supported by the Spanish Ministry of Economy and Competitiveness through project DPI2016-77869. The Titan V used for this research was donated by the NVIDIA Corporation.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A New Optical Density Granulometry-Based Descriptor for the Classification of Prostate Histological Images Using Shallow and Deep Gaussian Processes

  • Esteban, A. E.
  • López-Pérez, Miguel
  • Sales, Maria A.
  • Molina, Rafael
  • Colomer, Adrián|||0000-0002-7616-6029
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
[EN] Background and objective Prostate cancer is one of the most common male tumors. The increasing use of whole slide digital scanners has led to an enormous interest in the application of machine learning techniques to histopathological image classification. Here we introduce a novel family of morphological descriptors which, extracted in the appropriate image space and combined with shallow and deep Gaussian process based classifiers, improves early prostate cancer diagnosis. Method We decompose the acquired RGB image in its RGB and optical density hematoxylin and eosin components. Then, we define two novel granulometry-based descriptors which work in both, RGB and optical density, spaces but perform better when used on the latter. In this space they clearly encapsulate knowledge used by pathologists to identify cancer lesions. The obtained features become the inputs to shallow and deep Gaussian process classifiers which achieve an accurate prediction of cancer. Results We have used a real and unique dataset. The dataset is composed of 60 Whole Slide Images. For a five fold cross validation, shallow and deep Gaussian Processes obtain area under ROC curve values higher than 0.98. They outperform current state of the art patch based shallow classifiers and are very competitive to the best performing deep learning method. Models were also compared on 17 Whole Slide test Images using the FROC curve. With the cost of one false positive, the best performing method, the one layer Gaussian process, identifies 83.87% (sensitivity) of all annotated cancer in the Whole Slide Image. This result corroborates the quality of the extracted features, no more than a layer is needed to achieve excellent generalization results. Conclusion Two new descriptors to extract morphological features from histological images have been proposed. They collect very relevant information for cancer detection. From these descriptors, shallow and deep Gaussian Processes are capable of extracting the complex structure of prostate histological images. The new space/descriptor/classifier paradigm outperforms state-of-art shallow classifiers. Furthermore, despite being much simpler, it is competitive to state-of-art CNN architectures both on the proposed SICAPv1 database and on an external database, This work was supported by the Ministerio de Economia y Competitividad through project DPI2016-77869. The Titan V used for this research was donated by the NVIDIA Corporation
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

WeGleNet: A Weakly-Supervised Convolutional Neural Network for the Semantic Segmentation of Gleason Grades in Prostate Histology Images

  • Silva-Rodríguez, Julio
  • Colomer, Adrián|||0000-0002-7616-6029
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
[EN] Background and objective: Prostate cancer is one of the main diseases affecting men worldwide. The Gleason scoring system is the primary diagnostic tool for prostate cancer. This is obtained via the visual analysis of cancerous patterns in prostate biopsies performed by expert pathologists, and the aggregation of the main Gleason grades in a combined score. Computer-aided diagnosis systems allow to reduce the workload of pathologists and increase the objectivity. Nevertheless, those require a large number of labeled samples, with pixel level annotations performed by expert pathologists, to be developed. Recently, efforts have been made in the literature to develop algorithms aiming the direct estimation of the global Gleason score at biopsy/core level with global labels. However, these algorithms do not cover the accurate localization of the Gleason patterns into the tissue. These location maps are the basis to provide a reliable computer-aided diagnosis system to the experts to be used in clinical practice by pathologists. In this work, we propose a deep-learning-based system able to detect local cancerous patterns in the prostate tissue using only the global-level Gleason score obtained from clinical records during training. Methods: The methodological core of this work is the proposed weakly-supervised-trained convolutional neural network, WeGleNet, based on a multi-class segmentation layer after the feature extraction module, a global aggregation, and the slicing of the background class for the model loss estimation during training. Results: Using a public dataset of prostate tissue-micro arrays, we obtained a Cohen's quadratic kappa (kappa) of 0.67 for the pixel-level prediction of cancerous patterns in the validation cohort. We compared the model performance for semantic segmentation of Gleason grades with supervised state-of-the-art architectures in the test cohort. We obtained a pixel-level kappa of 0.61 and a macro-averaged f1-score of 0.58, at the same level as fully-supervised methods. Regarding the estimation of the core-level Gleason score, we obtained a kappa of 0.76 and 0.67 between the model and two different pathologists. Conclusions: WeGleNet is capable of performing the semantic segmentation of Gleason grades similarly to fully supervised methods without requiring pixel-level annotations. Moreover, the model reached a performance at the same level as inter-pathologist agreement for the global Gleason scoring of the cores., This work was supported by the Spanish Ministry of Economy and Competitiveness through projects DPI2016-77869 and PID2019-105142RB-C21.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A deep embedded refined clustering approach for breast cancer distinction based on DNA methylation

  • del Amor, Rocío
  • Colomer, Adrián|||0000-0002-7616-6029
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
  • Monteagudo, Carlos
[EN] Epigenetic alterations have an important role in the development of several types of cancer. Epigenetic studies generate a large amount of data, which makes it essential to develop novel models capable of dealing with large-scale data. In this work, we propose a deep embedded refined clustering method for breast cancer differentiation based on DNA methylation. In concrete, the deep learning system presented here uses the levels of CpG island methylation between 0 and 1. The proposed approach is composed of two main stages. The first stage consists in the dimensionality reduction of the methylation data based on an autoencoder. The second stage is a clustering algorithm based on the soft assignment of the latent space provided by the autoencoder. The whole method is optimized through a weighted loss function composed of two terms: reconstruction and classification terms. To the best of the authors¿ knowledge, no previous studies have focused on the dimensionality reduction algorithms linked to classification trained end-to-end for DNA methylation analysis. The proposed method achieves an unsupervised clustering accuracy of 0.9927 and an error rate (%) of 0.73 on 137 breast tissue samples. After a second test of the deep-learning-based method using a different methylation database, an accuracy of 0.9343 and an error rate (%) of 6.57 on 45 breast tissue samples are obtained. Based on these results, the proposed algorithm outperforms other state-of-the-art methods evaluated under the same conditions for breast cancer classification based on DNA methylation data., This work has received funding from Horizon 2020, the European Union's Framework Programme for Research and Innovation, under grant Agreement No. 860627 (CLARIFY), the Spanish Ministry of Economy and Competitiveness through project PID2019105142RB-C21 (AI4SKIN) and SICAP (DPI2016-77869-C2-1-R) and GVA through Project PROMETEO/2019/109.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Retinal layer segmentation in rodent OCT images: Local intensity profiles &amp, fully convolutional neural networks

  • Morales, Sandra|||0000-0003-0763-1545
  • Colomer, Adrián|||0000-0002-7616-6029
  • Mossi García, José Manuel|||0000-0001-9083-3476
  • del Amor, Rocío
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
  • Woldbye, David
  • Klemp, Kristian
  • Larsen, Michael
[EN] Background and Objective: Optical coherence tomography (OCT) is a useful technique to monitor retinal layer state both in humans and animal models. Automated OCT analysis in rats is of great relevance to study possible toxic effect of drugs and other treatments before human trials. In this paper, two different approaches to detect the most significant retinal layers in a rat OCT image are presented. Methods: One approach is based on a combination of local horizontal intensity profiles along with a new proposed variant of watershed transformation and the other is built upon an encoder-decoder convolutional network architecture. Results: After a wide validation, an averaged absolute distance error of 3.77 +/- 2.59 and 1.90 +/- 0.91 mu m is achieved by both approaches, respectively, on a batch of the rat OCT database. After a second test of the deep-learning-based method using an unseen batch of the database, an averaged absolute distance error of 2.67 +/- 1.25 mu m is obtained. The rat OCT database used in this paper is made publicly available to facilitate further comparisons. Conclusions: Based on the obtained results, it was demonstrated the competitiveness of the first approach since outperforms the commercial Insight image segmentation software (Phoenix Research Labs) as well as its utility to generate labelled images for validation purposes speeding significantly up the ground truth generation process. Regarding the second approach, the deep-learning-based method improves the results achieved by the more conventional method and also by other state-of-the-art techniques. In addition, it was verified that the results of the proposed network can be generalized to new rat OCT images., Animal experiment permission was granted by the Danish Animal Experimentation Council (license number: 2017-15-020101213). We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan V GPU used for this research. This work has received funding from Horizon 2020, the European Union's Framework Programme for Research and Innovation, under grant agreement No. 732613 (GALAHAD Project), the Spanish Ministry of Economy and Competitiveness through project DPI2016-77869 and GVA through project PROMETEO/2019/109.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

First-Stage Prostate Cancer Identification on Histopathological Images: Hand-Driven versus Automatic Learning

  • García-Pardo, José Gabriel
  • Colomer, Adrián|||0000-0002-7616-6029
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
[EN] Analysis of histopathological image supposes the most reliable procedure to identify prostate cancer. Most studies try to develop computer aid-systems to face the Gleason grading problem. On the contrary, we delve into the discrimination between healthy and cancerous tissues in its earliest stage, only focusing on the information contained in the automatically segmented gland candidates. We propose a hand-driven learning approach, in which we perform an exhaustive hand-crafted feature extraction stage combining in a novel way descriptors of morphology, texture, fractals and contextual information of the candidates under study. Then, we carry out an in-depth statistical analysis to select the most relevant features that constitute the inputs to the optimised machine-learning classifiers. Additionally, we apply for the first time on prostate segmented glands, deep-learning algorithms modifying the popular VGG19 neural network. We fine-tuned the last convolutional block of the architecture to provide the model specific knowledge about the gland images. The hand-driven learning approach, using a nonlinear Support Vector Machine, reports a slight outperforming over the rest of experiments with a final multi-class accuracy of <mml:semantics>0.876 +/- 0.026</mml:semantics> in the discrimination between false glands (artefacts), benign glands and Gleason grade 3 glands., This work has been funded by the Ministry of Economy, Industry and Competitiveness under the SICAP project (DPI2016-77869-C2-1-R). The work of Gabriel Garcia has been supported by the State Research Spanish Agency PTA2017-14610-I.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Evaluation of fractal dimension effectiveness for damage detection in retinal background

  • Colomer, Adrián|||0000-0002-7616-6029
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
  • Mossi García, José Manuel|||0000-0001-9083-3476
  • Janvier, Thomas
[EN] This work investigates the characterization of bright lesions in retinal fundus images using texture analysis techniques. Exudates and drusen are evidences of retinal damage in diabetic retinopathy (DR) and age-related macular degeneration (AMD) respectively. An automatic detection of pathological tissues could make possible an early detection of these diseases. In this work, fractal analysis is explored in order to discriminate between pathological and healthy retinal texture. After a deep preprocessing step, in which spatial and colour normalization are performed, the fractal dimension is extracted locally by computing the Hurst exponent (H) along different directions. The greyscale image is described by the increments of the fractional Brownian motion model and the H parameter is computed by linear regression in the frequency domain. The ability of fractal dimension to detect pathological tissues is demonstrated using a home-made system, based on fractal analysis and Support Vector Machine, able to achieve around a 70% and 83% of accuracy in E-OPHTHA and DIARETDB1 public databases respectively. In a second experiment, the fractal descriptor is combined with texture information, extracted by the Local Binary Patterns, improving the bright lesion detection. Accuracy, sensitivity and specificity values higher than 89%, 80% and 90% respectively suggest that the method presented in this paper is a robust algorithm for describing retina texture and can be useful in the automatic detection of DR and AMD., This paper was supported by the European Union's Horizon 2020 research and innovation programme under the Project GALAHAD [H2020-ICT-2016-2017, 732613]. In addition, this work was partially funded by the Ministerio de Economia y Competitividad of Spain, Project SICAP [DPI2016-77869-C2-1-R]. The work of Adrian Colomer has been supported by the Spanish Government under a FPI Grant [BES-2014-067889]. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research.