EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Models

תקציר מקורי באנגליתarXiv:2606.06379v3 Announce Type: replace-cross Abstract: Medical vision-language models (VLMs) have shown increasing potential for clinical image interpretation, including lesion detection and report generation. However, their practical utility remains limited by insufficient sensitivity to subtle lesions, whose visual evidence is often sparse, low-contrast, and embedded within complex anatomical context. As local visual tokens are aggregated, these weak lesion cues can become underrepresented in global image representations, making them difficult for medical VLMs to recognize. Existing efforts to improve lesion sensitivity mainly rely on medical-domain vision-encoder pre-training, clinical-term-guided alignment, or trainable pathological representation enhancement. Although effective, th