Lesion-Aware Visual-Language Fusion for Automated Image Captioning of Ulcerative Colitis Endoscopic Examinations

Alexis Ivan Lopez Escamilla, Gilberto Ochoa, Sharib Al

We present a lesion-aware image captioning framework for ulcerative colitis (UC). The model integrates ResNet embeddings, Grad-CAM heatmaps, and CBAM-enhanced attention with a T5 d…