Version 1
: Received: 3 September 2024 / Approved: 3 September 2024 / Online: 4 September 2024 (18:03:35 CEST)
How to cite:
Touati, M.; Touati, R.; Nana, L.; Benzarti, F.; Ben Yahia, S. DRCCT: Enhancing Diabetic Retinopathy Classification with A Compact Convolutional Transformer. Preprints2024, 2024090303. https://doi.org/10.20944/preprints202409.0303.v1
Touati, M.; Touati, R.; Nana, L.; Benzarti, F.; Ben Yahia, S. DRCCT: Enhancing Diabetic Retinopathy Classification with A Compact Convolutional Transformer. Preprints 2024, 2024090303. https://doi.org/10.20944/preprints202409.0303.v1
Touati, M.; Touati, R.; Nana, L.; Benzarti, F.; Ben Yahia, S. DRCCT: Enhancing Diabetic Retinopathy Classification with A Compact Convolutional Transformer. Preprints2024, 2024090303. https://doi.org/10.20944/preprints202409.0303.v1
APA Style
Touati, M., Touati, R., Nana, L., Benzarti, F., & Ben Yahia, S. (2024). DRCCT: Enhancing Diabetic Retinopathy Classification with A Compact Convolutional Transformer. Preprints. https://doi.org/10.20944/preprints202409.0303.v1
Chicago/Turabian Style
Touati, M., Faouzi Benzarti and Sadok Ben Yahia. 2024 "DRCCT: Enhancing Diabetic Retinopathy Classification with A Compact Convolutional Transformer" Preprints. https://doi.org/10.20944/preprints202409.0303.v1
Abstract
Diabetic retinopathy, a common complication of diabetes, is further exacerbated by factors such as hypertension and obesity. This study introduces the Diabetic Retinopathy Convolutional Transformer (DRCT) model, which combines convolutional and transformer techniques to enhance the classification of retinal images. The DRCT model achieved an impressive average F1 score of 0.97, reflecting its high accuracy in detecting true positives while minimizing false positives. Throughout 100 training epochs, the model exhibited strong generalization capabilities, achieving superior validation accuracy with minimal overfitting. On a newly evaluated dataset, the model attained precision and recall scores of 96.93% and 98.89%, respectively, indicating a well-balanced handling of false positives and false negatives. The model's ability to classify retinal images into five distinct diabetic retinopathy categories demonstrates its potential to significantly improve automated diagnosis and aid in clinical decision-making.
Keywords
AI; diabetic retinopathy; deep learning; DRCCT; classification; transformer
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.