Autor según el artículo: Ali, Mohammed Yousef Salem; Jabreel, Mohammed; Valls, Aida; Baget, Marc; Abdel-Nasser, Mohamed
Departamento: Medicina i Cirurgia Enginyeria Informàtica i Matemàtiques
Autor/es de la URV: Abdelnasser Mohamed Mahmoud, Mohamed / Ali, Mohammed Yousef Salem / Baget Bernaldiz, Marc / Valls Mateu, Aïda
Palabras clave: Network Medical image analysis Image segmentation Diabetic retinopathy Deep learning Affine transformation augmentation
Resumen: Diagnosing some eye pathologies, such as diabetic retinopathy (DR), depends on accurately detecting retinal eye lesions. Automatic lesion-segmentation methods based on deep learning involve heavy-weight models and have yet to produce the desired quality of results. This paper presents a new deep learning method for segmenting the four types of DR lesions found in eye fundus images. The method, called LezioSeg, is based on multi-scale modules and gated skip connections. It has three components: (1) Two multi-scale modules, the first is atrous spatial pyramid pooling (ASPP), which is inserted at the neck of the network, while the second is added at the end of the decoder to improve the fundus image feature extraction; (2) ImageNet MobileNet encoder; and (3) gated skip connection (GSC) mechanism for improving the ability to obtain information about retinal eye lesions. Experiments using affine-based transformation techniques showed that this architecture improved the performance in lesion segmentation on the well-known IDRiD and E-ophtha datasets. Considering the AUPR standard metric, for the IDRiD dataset, we obtained 81% for soft exudates, 86% for hard exudates, 69% for hemorrhages, and 40% for microaneurysms. For the E-ophtha dataset, we achieved an AUPR of 63% for hard exudates and 37.5% for microaneurysms. These results show that our model with affine-based augmentation achieved competitive results compared to several cutting-edge techniques, but with a model with much fewer parameters.
Áreas temáticas: Signal processing Physics, applied Hardware and architecture Engineering, electrical & electronic Engenharias iv Electrical and electronic engineering Control and systems engineering Computer science, information systems Computer networks and communications
Acceso a la licencia de uso: https://creativecommons.org/licenses/by/3.0/es/
Direcció de correo del autor: marc.baget@urv.cat mohamed.abdelnasser@urv.cat mohammedyousefsalem.ali@estudiants.urv.cat aida.valls@urv.cat
Identificador del autor: 0000-0002-1074-2441 0000-0003-2639-0177 0000-0003-3616-7809
Fecha de alta del registro: 2024-10-12
Versión del articulo depositado: info:eu-repo/semantics/publishedVersion
Enlace a la fuente original: https://www.mdpi.com/2079-9292/12/24/4940
URL Documento de licencia: https://repositori.urv.cat/ca/proteccio-de-dades/
Referencia al articulo segun fuente origial: Electronics. 12 (24): 4940-
Referencia de l'ítem segons les normes APA: Ali, Mohammed Yousef Salem; Jabreel, Mohammed; Valls, Aida; Baget, Marc; Abdel-Nasser, Mohamed (2023). LezioSeg: Multi-Scale Attention Affine-Based CNN for Segmenting Diabetic Retinopathy Lesions in Images. Electronics, 12(24), 4940-. DOI: 10.3390/electronics12244940
DOI del artículo: 10.3390/electronics12244940
Entidad: Universitat Rovira i Virgili
Año de publicación de la revista: 2023
Tipo de publicación: Journal Publications