English

Enhancing Medical Visual Grounding via Knowledge-guided Spatial Prompts

Computer Vision and Pattern Recognition 2026-04-03 v1

Abstract

Medical Visual Grounding (MVG) aims to identify diagnostically relevant phrases from free-text radiology reports and localize their corresponding regions in medical images, providing interpretable visual evidence to support clinical decision-making. Although recent Vision-Language Models (VLMs) exhibit promising multimodal reasoning ability, their grounding remains insufficient spatial precision, largely due to a lack of explicit localization priors when relying solely on latent embeddings. In this work, we analyze this limitation from an attention perspective and propose KnowMVG, a Knowledge-prior and global-local attention enhancement framework for MVG in VLMs that explicitly strengthens spatial awareness during decoding. Specifically, we present a knowledge-enhanced prompting strategy that encodes phrase related medical knowledge into compact embeddings, together with a global-local attention that jointly leverages coarse global information and refined local cues to guide precise region localization. localization. This design bridges high-level semantic understanding and fine-grained visual perception without introducing extra textual reasoning overhead. Extensive experiments on four MVG benchmarks demonstrate that our KnowMVG consistently outperforms existing approaches, achieving gains of 3.0% in AP50 and 2.6% in mIoU over prior state-of-the-art methods. Qualitative and ablation studies further validate the effectiveness of each component.

Keywords

Cite

@article{arxiv.2604.01915,
  title  = {Enhancing Medical Visual Grounding via Knowledge-guided Spatial Prompts},
  author = {Yifan Gao and Tao Zhou and Yi Zhou and Ke Zou and Yizhe Zhang and Huazhu Fu},
  journal= {arXiv preprint arXiv:2604.01915},
  year   = {2026}
}

Comments

10 pages, 6 figures

R2 v1 2026-07-01T11:50:48.996Z