Advanced Segmentation of Diabetic Retinopathy Lesions Using DeepLabv3+

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Boulaabi, Meher, Gader, Takwa Ben Aïcha, Echi, Afef Kacem, Mbarek, Sameh
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909591767351296
author Boulaabi, Meher
Gader, Takwa Ben Aïcha
Echi, Afef Kacem
Mbarek, Sameh
author_facet Boulaabi, Meher
Gader, Takwa Ben Aïcha
Echi, Afef Kacem
Mbarek, Sameh
contents To improve the segmentation of diabetic retinopathy lesions (microaneurysms, hemorrhages, exudates, and soft exudates), we implemented a binary segmentation method specific to each type of lesion. As post-segmentation, we combined the individual model outputs into a single image to better analyze the lesion types. This approach facilitated parameter optimization and improved accuracy, effectively overcoming challenges related to dataset limitations and annotation complexity. Specific preprocessing steps included cropping and applying contrast-limited adaptive histogram equalization to the L channel of the LAB image. Additionally, we employed targeted data augmentation techniques to further refine the model's efficacy. Our methodology utilized the DeepLabv3+ model, achieving a segmentation accuracy of 99%. These findings highlight the efficacy of innovative strategies in advancing medical image analysis, particularly in the precise segmentation of diabetic retinopathy lesions. The IDRID dataset was utilized to validate and demonstrate the robustness of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2504_17306
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Advanced Segmentation of Diabetic Retinopathy Lesions Using DeepLabv3+
Boulaabi, Meher
Gader, Takwa Ben Aïcha
Echi, Afef Kacem
Mbarek, Sameh
Computer Vision and Pattern Recognition
Artificial Intelligence
To improve the segmentation of diabetic retinopathy lesions (microaneurysms, hemorrhages, exudates, and soft exudates), we implemented a binary segmentation method specific to each type of lesion. As post-segmentation, we combined the individual model outputs into a single image to better analyze the lesion types. This approach facilitated parameter optimization and improved accuracy, effectively overcoming challenges related to dataset limitations and annotation complexity. Specific preprocessing steps included cropping and applying contrast-limited adaptive histogram equalization to the L channel of the LAB image. Additionally, we employed targeted data augmentation techniques to further refine the model's efficacy. Our methodology utilized the DeepLabv3+ model, achieving a segmentation accuracy of 99%. These findings highlight the efficacy of innovative strategies in advancing medical image analysis, particularly in the precise segmentation of diabetic retinopathy lesions. The IDRID dataset was utilized to validate and demonstrate the robustness of our approach.
title Advanced Segmentation of Diabetic Retinopathy Lesions Using DeepLabv3+
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2504.17306