Artificial intelligence for early detection of diabetic retinopathy: A vision transformer-based approach.

AI / informaticsPloS one· 2026

Artificial intelligence for early detection of diabetic retinopathy: A vision transformer-based approach.

Asma ElAdel, Imen Filali, Mourad Zaied

Read paper

RetinaAI / informaticsDiagnosisQ1IF 3.0

Vision transformer artificial intelligence model detects diabetic retinopathy with high accuracy

Artificial intelligence for early detection of diabetic retinopathy: A vision transformer-based approach.

Asma ElAdel … Mourad Zaied

PloS one · 2026

Background

Early identification of diabetic retinopathy (diabetic retinopathy), which is a primary cause of vision impairment globally, is a crucial phasis for effective intervention and treatment.

Methods

This paper proposes a Vision Transformer (Vision Transformer)-based model, specifically using a Compact Convolutional Transformer (Compact Convolutional Transformer), for early automated detection of diabetic retinopathy.

97%

Results

97%

correctly identified diabetic eye disease in nearly all cases checked

“

Conclusion

These results highlight the potential of transformer-based designs in medical picture analysis, as well as the implications for telemedicine and e-health solutions in real-time, especially in cases of low-resource settings.

Artificial intelligence for early detection of diabetic retinopathy: A vision transformer-based approach.

Artificial intelligence for early detection of diabetic retinopathy: A vision transformer-based approach.

Related papers