收录解读
临床多模态大模型的部署面临异构2D和3D医学图像理解及评估对齐的挑战。
提出ClinFusion,包含级联空间感知局部融合算子(Cascade Spatial-Aware Locality Fusion)的视觉编码器,以及基于视觉的评估框架MedIF-Bench和RoI接地指标。
在24项基准测试中20项超越开源模型,在16项中13项优于GPT-5.2和Gemini-3-Flash;放射科医生盲评确认其报告质量最高,且RoI指标与专家判断相关性最强。
该工作系统提升了医学视觉-语言理解的实证性能,但主要针对医学影像领域,通用性有限;评估框架和编码器设计具有可复用性,但尚未在非医学领域验证。
原始摘要
Multimodal large language models (MLLMs) hold immense potential to revolutionize clinical practice, yet deploying them in the medical domain is fundamentally a vision-centric challenge: models must absorb knowledge from heterogeneous 2D and 3D medical images, and evaluation protocols must align with radiologists' clinical practice and provide an accurate, fine-grained and factualness-driven assessment. In this paper, we introduce ClinFusion, a vision-centric MLLM designed for holistic medical understanding that systematically addresses these limitations. We propose a compositional and cascaded vision encoder architecture featuring a Cascade Spatial-Aware Locality Fusion operator that unifies diverse 2D and native 3D medical image understanding within a fused encoder. We further introduce a vision-grounded evaluation framework, including MedIF-Bench for instruction-following assessment and a region-of-interest-grounded method for clinically aligned and factualness-driven report generation evaluation. We show that ClinFusion sets a new state-of-the-art across a comprehensive suite of 2D and 3D multimodal medical benchmarks---spanning visual question answering, report generation, and instruction following---as well as textual medical tasks, outperforming leading open-source medical MLLMs (\textit{e.g.}, Hulu-Med, Lingshu) on 20 out of 24 benchmarks and demonstrating multimodal capabilities better than powerful proprietary models such as GPT-5.2 and Gemini-3-Flash on 13 out of 16 benchmarks, and can be further augmented with agentic tool use for retrieval-augmented and tool-assisted clinical workflows. A blinded evaluation by board-certified radiologists confirms that ClinFusion produces the highest-ranked reports, and validates our RoI-grounded metric as achieving the strongest correlation with expert judgment among all automatic evaluation metrics examined.