ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Hangjie Yuan, Yichen Qian, Zhiwei Tang, Xianzhe Xu, Lirong Wu, Sicheng Yang, Jinwang Wang, Pengju Wang, Zhitao Zeng, Yizeng Han, Yan Xing, Shengxuan Luo, Tao Feng, Qing Xie, Weigen Yao, Yi Yang, Zuozhu Liu, Jiasheng Tang, Shaocheng Wang, Jitao Wang, Jiahong Dong, Weihua Chen, Feng Xu, Fan Wang
• Venue: arXiv: cs.CV
• Published: 2026-07-27
• Collected: 2026-07-28
• URL: http://arxiv.org/abs/2607.24743v1
• PDF: https://arxiv.org/pdf/2607.24743v1
• DOI: UNKNOWN

Plain-Language Brief

The paper introduces ClinFusion, a multimodal large language model designed for holistic medical understanding. It can handle both 2D and 3D medical images and outperforms other open-source and proprietary models on various medical benchmarks. A study by board-certified radiologists confirms that ClinFusion produces the highest-ranked reports.

What the Document Says

• The paper presents ClinFusion, a vision-centric multimodal large language model designed for comprehensive medical understanding.
• It features a Cascade Spatial-Aware Locality Fusion operator that unifies 2D and native 3D medical image understanding within a fused encoder.
• The authors propose 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.
• ClinFusion outperforms leading open-source medical MLLMs like Hulu-Med and Lingshu on 20 out of 24 benchmarks, demonstrating multimodal capabilities better than GPT-5.2 and Gemini-3-Flash on 13 out of 16 benchmarks.
• The model can be 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 their RoI-grounded metric achieves the strongest correlation with expert judgment among all automatic evaluation metrics examined.

Key Concepts Mentioned

• ClinFusion
• multimodal large language model
• medical images
• evaluation framework
• MedIF-Bench
• region-of-interest-grounded method
• open-source medical MLLMs
• GPT-5.2
• Gemini-3-Flash
• radiologists' evaluation
• clinically aligned
• factualness-driven

Claims Made by the Document

• ClinFusion outperforms other open-source and proprietary models on various medical benchmarks.
• A blinded evaluation by board-certified radiologists confirms that ClinFusion produces the highest-ranked reports.

Evidence Used

• It outperforms leading open-source medical MLLMs on 20 out of 24 benchmarks and demonstrates multimodal capabilities better than powerful proprietary models on 13 out of 16 benchmarks.
• A blinded evaluation by board-certified radiologists confirms that ClinFusion produces the highest-ranked reports.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.