Lightweight Convolutional Neural Networks for Retinal Disease Classification

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Qasim, Duaa Kareem, Jebur, Sabah Abdulazeez, Ali, Lafta Raheem, Khalaf, Abdul Jalil M., Hussain, Abir Jaafar
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916777336766464
author Qasim, Duaa Kareem
Jebur, Sabah Abdulazeez
Ali, Lafta Raheem
Khalaf, Abdul Jalil M.
Hussain, Abir Jaafar
author_facet Qasim, Duaa Kareem
Jebur, Sabah Abdulazeez
Ali, Lafta Raheem
Khalaf, Abdul Jalil M.
Hussain, Abir Jaafar
contents Retinal diseases such as Diabetic Retinopathy (DR) and Macular Hole (MH) significantly impact vision and affect millions worldwide. Early detection is crucial, as DR, a complication of diabetes, damages retinal blood vessels, potentially leading to blindness, while MH disrupts central vision, affecting tasks like reading and facial recognition. This paper employed two lightweight and efficient Convolution Neural Network architectures, MobileNet and NASNetMobile, for the classification of Normal, DR, and MH retinal images. The models were trained on the RFMiD dataset, consisting of 3,200 fundus images, after undergoing preprocessing steps such as resizing, normalization, and augmentation. To address data scarcity, this study leveraged transfer learning and data augmentation techniques, enhancing model generalization and performance. The experimental results demonstrate that MobileNetV2 achieved the highest accuracy of 90.8%, outperforming NASNetMobile, which achieved 89.5% accuracy. These findings highlight the effectiveness of CNNs in retinal disease classification, providing a foundation for AI-assisted ophthalmic diagnosis and early intervention.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03186
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Lightweight Convolutional Neural Networks for Retinal Disease Classification
Qasim, Duaa Kareem
Jebur, Sabah Abdulazeez
Ali, Lafta Raheem
Khalaf, Abdul Jalil M.
Hussain, Abir Jaafar
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Neural and Evolutionary Computing
Retinal diseases such as Diabetic Retinopathy (DR) and Macular Hole (MH) significantly impact vision and affect millions worldwide. Early detection is crucial, as DR, a complication of diabetes, damages retinal blood vessels, potentially leading to blindness, while MH disrupts central vision, affecting tasks like reading and facial recognition. This paper employed two lightweight and efficient Convolution Neural Network architectures, MobileNet and NASNetMobile, for the classification of Normal, DR, and MH retinal images. The models were trained on the RFMiD dataset, consisting of 3,200 fundus images, after undergoing preprocessing steps such as resizing, normalization, and augmentation. To address data scarcity, this study leveraged transfer learning and data augmentation techniques, enhancing model generalization and performance. The experimental results demonstrate that MobileNetV2 achieved the highest accuracy of 90.8%, outperforming NASNetMobile, which achieved 89.5% accuracy. These findings highlight the effectiveness of CNNs in retinal disease classification, providing a foundation for AI-assisted ophthalmic diagnosis and early intervention.
title Lightweight Convolutional Neural Networks for Retinal Disease Classification
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2506.03186