DeepRetina: Transformer-Enhanced EfficientNet for Retinal Disease Classification

Title

DeepRetina: Transformer-Enhanced EfficientNet for Retinal Disease Classification

Creator

James, Maria; Ramamurthy, B.; Saravanan, K.N.

Description

Retinal diseases are a major cause of visual impairment in India, which requires precise and automated diagnosis tools.This paper, introduce a two-phase deep learning architecture for classifying five common retinal ailments: Glaucoma, Normal Fundus, Pathological Myopia, Hypertensive Retinopathy, and Cataract. A Swin Transformer (Swin-T) was fine-tuned on augmented retinal fundus images in the first phase to extract domain-adapted feature representations. The transformer utilize such embeddings for learning a regularized EfficientNet-inspired classifier in the second phase, with mixup augmentation and label smoothing for improving generalizability. Comprehensive experiments conducted on a carefully curated dataset of 643 test images validate that our method attains a test accuracy of 93.93%, with high precision as well as recall across all categories. The suggested pipeline strikes a suitable balance between feature abundance with transformer-based adaptation and resilient classification with EfficientNet, providing a viable tool for automated diagnosis of retinal ailments in practical clinical scenarios. 2026 IEEE.

Source

2026 6th International Conference on Advances in Electrical, Computing, Communications and Sustainable Technologies, ICAECT 2026;

Date

01-01-2026

Publisher

Institute of Electrical and Electronics Engineers Inc.

Subject

EfficientNet; Glaucoma; Hypertensive Retinopathy and Cataract; Normal Fundus; Pathological Myopia; Swin Transformer

Coverage

James M., Christ (Deemed to be University), Department of Computer Science, Bangalore, India; Ramamurthy B., Christ (Deemed to be University), Department of Computer Science, Bangalore, India; Saravanan K.N., Christ (Deemed to be University), Department of Computer Science, Bangalore, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISBN: 979-833157322-5;

Format

online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1109/ICAECT68478.2026.11426056

https://www.scopus.com/pages/publications/105035740290?origin=resultslist