Mostrar o rexistro simple do ítem
Weakly-supervised detection of AMD-related lesions in color fundus images using explainable deep learning
dc.contributor.author | Morano, José | |
dc.contributor.author | Hervella, Álvaro S. | |
dc.contributor.author | Rouco, J. | |
dc.contributor.author | Novo Buján, Jorge | |
dc.contributor.author | Fernández-Vigo, José Ignacio | |
dc.contributor.author | Ortega Hortas, Marcos | |
dc.date.accessioned | 2023-03-30T17:37:22Z | |
dc.date.available | 2023-03-30T17:37:22Z | |
dc.date.issued | 2023-02 | |
dc.identifier.issn | 0169-2607 | |
dc.identifier.uri | http://hdl.handle.net/2183/32816 | |
dc.description.abstract | [Abstract]: Background and Objectives: Age-related macular degeneration (AMD) is a degenerative disorder affecting the macula, a key area of the retina for visual acuity. Nowadays, AMD is the most frequent cause of blindness in developed countries. Although some promising treatments have been proposed that effectively slow down its development, their effectiveness significantly diminishes in the advanced stages. This emphasizes the importance of large-scale screening programs for early detection. Nevertheless, implementing such programs for a disease like AMD is usually unfeasible, since the population at risk is large and the diagnosis is challenging. For the characterization of the disease, clinicians have to identify and localize certain retinal lesions. All this motivates the development of automatic diagnostic methods. In this sense, several works have achieved highly positive results for AMD detection using convolutional neural networks (CNNs). However, none of them incorporates explainability mechanisms linking the diagnosis to its related lesions to help clinicians to better understand the decisions of the models. This is specially relevant, since the absence of such mechanisms limits the application of automatic methods in the clinical practice. In that regard, we propose an explainable deep learning approach for the diagnosis of AMD via the joint identification of its associated retinal lesions. Methods: In our proposal, a CNN with a custom architectural setting is trained end-to-end for the joint identification of AMD and its associated retinal lesions. With the proposed setting, the lesion identification is directly derived from independent lesion activation maps; then, the diagnosis is obtained from the identified lesions. The training is performed end-to-end using image-level labels. Thus, lesion-specific activation maps are learned in a weakly-supervised manner. The provided lesion information is of high clinical interest, as it allows clinicians to assess the developmental stage of the disease. Additionally, the proposed approach allows to explain the diagnosis obtained by the models directly from the identified lesions and their corresponding activation maps. The training data necessary for the approach can be obtained without much extra work on the part of clinicians, since the lesion information is habitually present in medical records. This is an important advantage over other methods, including fully-supervised lesion segmentation methods, which require pixel-level labels whose acquisition is arduous. Results: The experiments conducted in 4 different datasets demonstrate that the proposed approach is able to identify AMD and its associated lesions with satisfactory performance. Moreover, the evaluation of the lesion activation maps shows that the models trained using the proposed approach are able to identify the pathological areas within the image and, in most cases, to correctly determine to which lesion they correspond. Conclusions: The proposed approach provides meaningful information—lesion identification and lesion activation maps—that conveniently explains and complements the diagnosis, and is of particular interest to clinicians for the diagnostic process. Moreover, the data needed to train the networks using the proposed approach is commonly easy to obtain, what represents an important advantage in fields with particularly scarce data, such as medical imaging. | es_ES |
dc.description.sponsorship | Xunta de Galicia; ED481B-2022-025 | es_ES |
dc.description.sponsorship | Xunta de Galicia; ED431C 2020/24 | es_ES |
dc.description.sponsorship | Xunta de Galicia; IN845D 2020/38 | es_ES |
dc.description.sponsorship | Xunta de Galicia; ED481A 2021/140 | es_ES |
dc.description.sponsorship | Xunta de Galicia; ED431G 2019/01 | es_ES |
dc.description.sponsorship | This work was funded by Instituto de Salud Carlos III, Government of Spain, and the European Regional Development Fund (ERDF) of the European Union (EU) through the DTS18/00136 research project; Ministerio de Ciencia e Innovación, Government of Spain, through RTI2018-095894-B-I00 and PID2019-108435RB-I00 research projects; Axencia Galega de Innovación (GAIN), Xunta de Galicia, ref. IN845D 2020/38; Conselleria de Cultura, Educación e Universidade, Xunta de Galicia, through Grupos de Referencia Competitiva, ref. ED431C 2020/24, the predoctoral grant ref. ED481A 2021/140, and the postdoctoral grant ref. ED481B-2022-025; CITIC, Centro de Investigación de Galicia ref. ED431G 2019/01, is funded by Conselleria de Educación, Universidade e Formación Profesional, Xunta de Galicia, through the ERDF (80%) and Secretaria Xeral de Universidades (20%). | es_ES |
dc.language.iso | eng | es_ES |
dc.publisher | Elsevier Ireland Ltd | es_ES |
dc.relation | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/RTI2018-095894-B-I00/ES/DESARROLLO DE TECNOLOGIAS INTELIGENTES PARA DIAGNOSTICO DE LA DMAE BASADAS EN EL ANALISIS AUTOMATICO DE NUEVAS MODALIDADES HETEROGENEAS DE ADQUISICION DE IMAGEN OFTALMOLOGICA | es_ES |
dc.relation | info:eu-repo/grantAgreement/ISCIII/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/DTS18%2F00136/ES/PLATAFORMA ONLINE PARA PREVENCION Y DETECCION PRECOZ DE ENFERMEDAD VASCULAR MEDIANTE ANALISIS AUTOMATIZADO DE INFORMACION E IMAGEN CLINICA | es_ES |
dc.relation | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2019-108435RB-I00/ES/CUANTIFICACION Y CARACTERIZACION COMPUTACIONAL DE IMAGEN MULTIMODAL OFTALMOLOGICA: ESTUDIOS EN ESCLEROSIS MULTIPLE | es_ES |
dc.relation.uri | https://doi.org/10.1016/j.cmpb.2022.107296 | es_ES |
dc.rights | Atribución-NoComercial-SinDerivadas 3.0 España | es_ES |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ | * |
dc.subject | Age-related macular degeneration | es_ES |
dc.subject | Deep learning | es_ES |
dc.subject | Medical imaging | es_ES |
dc.subject | Ophthalmology | es_ES |
dc.title | Weakly-supervised detection of AMD-related lesions in color fundus images using explainable deep learning | es_ES |
dc.type | info:eu-repo/semantics/article | es_ES |
dc.rights.access | info:eu-repo/semantics/openAccess | es_ES |
UDC.journalTitle | Computer Methods and Programs in Biomedicine | es_ES |
UDC.volume | 229 | es_ES |
UDC.issue | February | es_ES |
Ficheiros no ítem
Este ítem aparece na(s) seguinte(s) colección(s)
-
GI-VARPA - Artigos [76]