EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Lightweight Attention-Enhanced U-Net Framework for Automated Multi-Class Diabetic Retinopathy Lesion Segmentation Using Retinal Fundus Image

Waghole Vinaya Vasant, Prof. Dr. Monika Rokade, Prof. Dr. Sunil Khatal

International Research Journal on Advanced Engineering and Management (IRJAEM) · 19.06.2026 · 4 (06) · 2410-2416

DOI: 10.47392/irjaem.2026.0347 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Research Journal on Advanced Engineering and Management (IRJAEM), online erschienen am 19.06.2026. Verfasst von Waghole Vinaya Vasant und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetic Retinopathy (DR) is a major diabetes-related eye disease that can cause permanent blindness if not diagnosed early. This paper presents a lightweight CNN-based U-Net framework for automated multi-class segmentation of retinal lesions from fundus images. The proposed system uses image preprocessing, data augmentation, and hybrid loss functions to improve segmentation accuracy and handle class imbalance. The model effectively detects lesions such as microaneurysms, hemorrhages, hard exudates, soft exudates, and optic disc regions using the IDRiD dataset. Experimental results demonstrate reliable performance in terms of Dice score, IoU, precision, and recall, supporting early diagnosis and clinical decision-making.

Zitieren

APA

Vasant, W. V., Rokade, P. D. M., & Khatal, P. D. S. (2026). Lightweight Attention-Enhanced U-Net Framework for Automated Multi-Class Diabetic Retinopathy Lesion Segmentation Using Retinal Fundus Image. International Research Journal on Advanced Engineering and Management (IRJAEM), 4(06), 2410-2416. https://doi.org/10.47392/irjaem.2026.0347

Vancouver

Vasant WV, Rokade PDM, Khatal PDS. Lightweight Attention-Enhanced U-Net Framework for Automated Multi-Class Diabetic Retinopathy Lesion Segmentation Using Retinal Fundus Image. International Research Journal on Advanced Engineering and Management (IRJAEM). 2026;4(06):2410-2416. doi:10.47392/irjaem.2026.0347

BibTeX
@article{Vasant2026,
  author = {Vasant, Waghole Vinaya and Rokade, Prof. Dr. Monika and Khatal, Prof. Dr. Sunil},
  title = {Lightweight Attention-Enhanced U-Net Framework for Automated Multi-Class Diabetic Retinopathy Lesion Segmentation Using Retinal Fundus Image},
  journal = {International Research Journal on Advanced Engineering and Management (IRJAEM)},
  year = {2026},
  volume = {4},
  number = {06},
  pages = {2410--2416},
  doi = {10.47392/irjaem.2026.0347}
}
Kostenlos starten →