Author, as appears in the article.: Khalid, S; Rashwan, HA; Abdulwahab, S; Abdel-Nasser, M; Quiroga, FM; Puig, D
Department: Enginyeria Informàtica i Matemàtiques
URV's Author/s: Abdelnasser Mohamed Mahmoud, Mohamed / Puig Valls, Domènec Savi
Keywords: Retinal image Quality assessment Ocular diseases Neural-network model Intepretability Gradability Explainability Deep learning Autoencoder network segmentation quality assessment ocular diseases intepretability gradability explainability diabetic-retinopathy deep learning autoencoder network
Abstract: The performance of diagnostic Computer-Aided Design (CAD) systems for retinal diseases depends on the quality of the retinal images being screened. Thus, many studies have been developed to evaluate and assess the quality of such retinal images. However, most of them did not investigate the relationship between the accuracy of the developed models and the quality of the visualization of interpretability methods for distinguishing between gradable and non-gradable retinal images. Consequently, this paper presents a novel framework called “FGR-Net” to automatically assess and interpret underlying fundus image quality by merging an autoencoder network with a classifier network. The FGR-Net model also provides an interpretable quality assessment through visualizations. In particular, FGR-Net uses a deep autoencoder to reconstruct the input image in order to extract the visual characteristics of the input fundus images based on self-supervised learning. The extracted features by the autoencoder are then fed into a deep classifier network to distinguish between gradable and ungradable fundus images. FGR-Net is evaluated with different interpretability methods, which indicates that the autoencoder is a key factor in forcing the classifier to focus on the relevant structures of the fundus images, such as the fovea, optic disk, and prominent blood vessels. Additionally, the interpretability methods can provide visual feedback for ophthalmologists to understand how our model evaluates the quality of fundus images. The experimental results showed the superiority of FGR-Net over the state-of-the-art quality assessment methods, with an accuracy of >89% and an F1-score of >87%. The code is publicly available at https://github.com/saifalkh/FGR-Net.
Thematic Areas: Química Operations research & management science Medicina iii Medicina ii Medicina i Materiais Matemática / probabilidade e estatística Interdisciplinar Geociências General engineering Farmacia Engineering, electrical & electronic Engineering (miscellaneous) Engineering (all) Engenharias iv Engenharias iii Engenharias ii Engenharias i Enfermagem Educação Economia Direito Computer science, artificial intelligence Computer science applications Ciências sociais aplicadas i Ciências biológicas iii Ciências biológicas ii Ciências biológicas i Ciências ambientais Ciências agrárias i Ciência da computação Biotecnología Biodiversidade Astronomia / física Artificial intelligence Arquitetura, urbanismo e design Administração, ciências contábeis e turismo Administração pública e de empresas, ciências contábeis e turismo
licence for use: https://creativecommons.org/licenses/by/3.0/es/
Author's mail: mohamed.abdelnasser@urv.cat domenec.puig@urv.cat
Author identifier: 0000-0002-1074-2441 0000-0002-0562-4205
Record's date: 2023-12-16
Papper version: info:eu-repo/semantics/publishedVersion
Link to the original source: https://www.sciencedirect.com/science/article/pii/S0957417423021462
Licence document URL: http://repositori.urv.cat/ca/proteccio-de-dades/
Papper original source: Expert Systems With Applications. 238
APA: Khalid, S; Rashwan, HA; Abdulwahab, S; Abdel-Nasser, M; Quiroga, FM; Puig, D (2024). FGR-Net: Interpretable fundus image gradeability classification based on deep reconstruction learning. Expert Systems With Applications, 238(), -. DOI: 10.1016/j.eswa.2023.121644
Article's DOI: 10.1016/j.eswa.2023.121644
Entity: Universitat Rovira i Virgili
Journal publication year: 2024
Publication Type: Journal Publications
Repositori URV