Pasar al contenido principal

ANALISIS DE IMAGEN DE FONDO DE OJO PARA CRIBADO AUTOMATICO DE ENFERMEDADES OFTALMOLOGICAS

TIN2013-46751-R

•
Nombre agencia financiadora Ministerio de Economía y Competitividad
Acrónimo agencia financiadora MINECO
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2013
Plan Estatal 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Unidad de gestión Secretaría de Estado de Educación, Formación Profesional y Universidades
Centro beneficiario UNIVERSITAT POLITÈCNICA DE VALÈNCIA
Identificador persistente http://dx.doi.org/10.13039/501100003329

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

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

CNNs for Automatic Glaucoma Assessment using Fundus Images: An Extensive Validation

  • Díaz-Pinto, Andrés Yesid
  • Köhler, Thomas
  • Navea, Amparo
  • Morales, Sandra|||0000-0003-0763-1545
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
  • Mossi García, José Manuel|||0000-0001-9083-3476
[EN] Background: Most current algorithms for automatic glaucoma assessment using fundus images rely on handcrafted features based on segmentation, which are affected by the performance of the chosen segmentation method and the extracted features. Among other characteristics, Convolutional Neural Networks (CNNs) are known because of their ability to learn highly discriminative features from raw pixel intensities. Methods: In this paper, we employed five different ImageNet-trained models (VGG16, VGG19, InceptionV3, ResNet50 and Xception) for automatic glaucoma assessment using fundus images. Results from an extensive validation using cross-validation and cross-testing strategies were compared with previous works in the literature. Results: Using five public databases (1707 images), an average AUC of 0.9605 with a 95% confidence interval of 95.92% - 97.07%, an average specificity of 0.8580 and an average sensitivity of 0.9346 were obtained after using the Xception architecture, significantly improving the performance of other state-of-the-art works. Moreover, a new clinical database, ACRIMA, has been made publicly available, containing 705 labelled images. It is composed of 396 glaucomatous images and 309 normal images, which means, the largest public database for glaucoma diagnosis. The high specificity and sensitivity obtained from the proposed approach are supported by an extensive validation using not only the cross-validation strategy but also the cross-testing validation on, to the best of the authors' knowledge, all publicly available glaucoma-labelled databases. Conclusions:These results suggest that using ImageNet-trained models is a robust alternative for automatic glaucoma screening system. All images, CNN weights and software used to fine-tune and test the five CNNs are publicly available, which could be used as a testbed for further comparisons., This work was supported by the Ministerio de Economia y Competitividad of Spain, Project ACRIMA [TIN2013-46751-R] and the Project GALAHAD [H2020-ICT-2016-2017, 732613]. In particular, the work of Andres Diaz-Pinto has been supported by the Generalitat Valenciana under the scholarship Santiago Grisolia [GRISOLIA/2015/027]. (Corresponding author: Andres Diaz-Pinto). We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan V GPU used for this research.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Assessment of sparse-based inpainting for retinal vessel removal

  • Colomer, Adrián|||0000-0002-7616-6029
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
  • Engan, Kjersti
  • Skretting, Karl
[EN] Some important eye diseases, like macular degeneration or diabetic retinopathy, can induce changes visible on the retina, for example as lesions. Segmentation of lesions or extraction of textural features from the fundus images are possible steps towards automatic detection of such diseases which could facilitate screening as well as provide support for clinicians. For the task of detecting significant features, retinal blood vessels are considered as being interference on the retinal images. If these blood vessel structures could be suppressed, it might lead to a more accurate segmentation of retinal lesions as well as a better extraction of textural features to be used for pathology detection. This work proposes the use of sparse representations and dictionary learning techniques for retinal vessel inpainting. The performance of the algorithm is tested for greyscale and RGB images from the DRIVE and STARE public databases, employing different neighbourhoods and sparseness factors. Moreover, a comparison with the most common inpainting family, diffusion-based methods, is carried out. For this purpose, two different ways of assessing the quality of the inpainting are presented and used to evaluate the results of the non-artificial inpainting, i.e. where a reference image does not exist. The results suggest that the use of sparse-based inpainting performs very well for retinal blood vessels removal which will be useful for the future detection and classification of eye diseases. (C) 2017 Elsevier B.V. All rights reserved., This work was supported by NILS Science and Sustainability Programme (014-ABEL-IM-2013) and by the Ministerio de Economia y Competitividad of Spain, Project ACRIMA (TIN2013-46751-R). The work of Adrian Colomer has been supported by the Spanish Government under the FPI Grant BES-2014-067889.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Retinal Disease Screening through Local Binary Patterns

  • Morales, Sandra|||0000-0003-0763-1545
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
  • Colomer, Adrián|||0000-0002-7616-6029
  • Engan, Kjersti
This work investigates discrimination capabilities in the texture of fundus images to differentiate between pathological and healthy images. For this purpose, the performance of Local Binary Patterns (LBP) as a texture descriptor for retinal images has been explored and compared with other descriptors such as LBP filtering (LBPF) and local phase quantization (LPQ). The goal is to distinguish between diabetic retinopathy (DR), agerelated macular degeneration (AMD) and normal fundus images analysing the texture of the retina background and avoiding a previous lesion segmentation stage. Five experiments (separating DR from normal, AMD from normal, pathological from normal, DR from AMD and the three different classes) were designed and validated with the proposed procedure obtaining promising results. For each experiment, several classifiers were tested. An average sensitivity and specificity higher than 0.86 in all the cases and almost of 1 and 0.99, respectively, for AMD detection were achieved. These results suggest that the method presented in this paper is a robust algorithm for describing retina texture and can be useful in a diagnosis aid system for retinal disease screening., This work was supported by NILS Science and Sustainability Programme (010-ABEL-IM-2013) and by the Ministerio de Economia y Competitividad of Spain, Project ACRIMA (TIN2013-46751-R). The work of A. Colomer was supported by the Spanish Government under the FPI Grant BES-2014-067889.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Retinal network characterization through fundus image processing: Significant point identification on vessel centerline

  • Morales, Sandra|||0000-0003-0763-1545
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
  • Angulo, Jesus
  • Legaz-Aparicio, Alvar-Gines
  • Verdu-Monedero, Rafael
[EN] This paper describes a new approach for significant point identification on vessel centerline. Significant points such as bifurcations and crossovers are able to define and characterize the retinal vascular network. In particular, hit-or-miss transformation is used to detect terminal, bifurcation and simple crossing points but a post-processing stage is needed to identify complex intersections. This stage focuses on the idea that the intersection of two vessels creates a sort of close loop formed by the vessels and this effect can be used to differentiate a bifurcation from a crossover. Experimental results show quantitative improvements by increasing the number of true positives and reducing the false positives and negatives in the significant point detection when the proposed method is compared with another state-of-the-art work. A sensitivity equal to 1 and a predictive positive value of 0.908 was achieved in the analyzed cases. Hit-or-miss transformation must be applied on a binary skeleton image. Therefore, a method to extract the vessel skeleton in a direct way is also proposed. Although the identification of the significant points of the retinal tree can be useful by itself for multiple applications such as biometrics and image registration, this paper presents an algorithm that makes use of the significant points to measure the bifurcation angles of the retinal network which can be related to cardiovascular risk determination., This work was supported by the Ministerio de Economia y Conipetitividad of Spain, Project ACRIMA (TIN2013-46751-R). The authors would like to thank people who provide the public databases used in this work (DRIVE, STARE and VARIA).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Computer-Aided Diagnosis Software for Hypertensive Risk Determination Through Fundus Image Processing

  • Morales, Sandra|||0000-0003-0763-1545
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
  • Alcañiz Raya, Mariano Luis|||0000-0001-9207-0636
  • Navea, Amparo
The goal of the software proposed in this paper is to assist ophthalmologists in diagnosis and disease prevention, helping them to determine cardiovascular risk or other diseases where the vessels can be altered, as well as to monitor the pathology progression and response to different treatments. The performance of the tool has been evaluated by means of a double-blind study where its sensitivity, specificity, and reproducibility to discriminate between health fundus (without cardiovascular risk) and hypertensive patients has been calculated in contrast to an expert ophthalmologist opinion obtained through a visual inspection of the fundus image. An improvement of almost 20% has been achieved comparing the system results with the clinical visual classification., This work was supported in part by Ministerio de Economia y Competitividad of Spain, Project ACRIMA (TIN2013-46751-R) and partially by the Projects Consolider-C (SEJ2006 14301/PSIC), CIBER of Physiopathology of Obesity and Nutrition, an initiative of ISCIII, and the Excellence Research Program PROMETEO (Generalitat Valenciana. Conselleria de Educacion, 2008157).