Ramzan Talib

Clinical-guided deep learning framework for diabetic retinopathy: integrating lesion-aware attention, adversarial augmentation, and uncertainty quantification

The global prevalence of diabetic retinopathy (DR) is increasing in parallel with the rising burden of diabetes, posing a substantial public health challenge. Current automated DR screening systems often lack lesion-level interpretable, robustness against class imbalance, and reliable uncertainty estimation, limiting t...