AI RESEARCH
Rad-VLSM: A Cross-Modal Framework with Semantics-Assisted Prompting for Medical Segmentation and Diagnosis
arXiv CS.CV
•
ArXi:2605.18130v1 Announce Type: new Medical image segmentation is clinically valuable when it s diagnosis rather than merely producing lesion masks. However, diagnostically relevant lesion cues are often subtle and localized, while existing models may be distracted by background tissues, acoustic artifacts, and irrelevant visual correlations. To address this problem, we propose Rad-VLSM, a two-stage cross-modal framework for semantics-assisted lesion focusing, robust segmentation, and visually grounded diagnosis.