상세 보기
초록
Although Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in Medical Visual Question Answering (Med-VQA), their reliance on global image features often lacks precise pixel-level grounding, thereby limiting clinical trustworthiness. To bridge the semantic gap between high-level clinical reasoning and spatial localization, we propose MedREAL (Medical REasoning-driven Answering and Localization), a unified framework that seamlessly aligns linguistic reasoning with spatial grounding. Specifically, MedREAL introduces Seg Anchored Reasoning Pooling (SARP) to distill task-relevant semantic evidence directly from [SEG] tokens within the MLLM’s hidden states. Furthermore, a Reasoning-to-Visual (R2V) fusion mechanism is proposed to effectively inject these reasoning-aware features into a segmentation pipeline for accurate mask decoding. To facilitate this paradigm, we construct MedRAVS-13K, a comprehensive dataset comprising 13,824 expertly validated samples across four diverse imaging modalities. Extensive experiments demonstrate that MedREAL significantly outperforms state-of-the-arts, achieving 68.49% gIoU and 70.47% cIoU on benchmark evaluations. By generating evidence masks that are strictly consistent with textual diagnoses, MedREAL provides a robust, interpretable framework for reasoning-driven medical image analysis. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
키워드
- 제목
- From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and Segmentation
- 저자
- Gu, Haowen; Pei, Gensheng; Mao, Junzhu; Wang, Qiong; Ren, Mingwu; Yao, Yazhou
- 발행일
- 2026
- 유형
- Proceedings Paper
- 권
- 17046 LNCS
- 페이지
- 19 ~ 36
- 언어
- ENG
- 출판사
- Springer Science and Business Media Deutschland GmbH
- 발행국가
- 미국
- 분량
- 18 페이지
- ISSN
- E 1611-3349
P 0302-9743