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

• URL: http://arxiv.org/abs/2607.24743v2
• Date: Tue, 28 Jul 2026 10:52:57 GMT
• Title: ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
• Abstract summary: 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.<n>We introduce ClinFusion, a vision-centric MLLM designed for holistic medical understanding.<n>We show that ClinFusion sets a new state-of-the-art across a comprehensive suite of 2D and 3D multimodal medical benchmarks.
• Score: 67.57715989349471
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation [66.62662330558906]
  CORAL is a multimodal framework that integrates spatial grounding and concept-level supervision into a unified reasoning process.<n>CORAL employs a prompt-driven medical segmentation model to localize lesions and predicts multi-class clinical attributes through a Concept Bottleneck module.<n>Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs.
  arXiv  Detail & Related papers  (2026-09-14T10:21:23Z)
• Can Multimodal Large Language Models Understand OCT? [3.932595394031011]
  multimodal large language models (MLLMs) have demonstrated considerable potential in medical image analysis.<n> OCT-Bench comprises 10,076 high-quality multiple-choice questions constructed from 4,137 OCT images across seven public datasets.<n>We systematically evaluate 20 representative MLLMs, including proprietary models, open-source general-purpose models, and medical-domain models.
  arXiv  Detail & Related papers  (2026-07-18T03:08:31Z)
• Brain-Adapter: A Dual-Stream Vision-Language MIL Framework for Comprehensive 3D CT Diagnosis of Acute Intracranial Pathologies [8.984636910625886]
  Brain-Adapter is a novel dual-stream multiple instance learning framework.<n>Our method significantly outperforms state-of-the-art 3D models and standard MIL approaches.
  arXiv  Detail & Related papers  (2026-06-22T15:41:16Z)
• MMBU: A Massive Multi-modal Biomedical Understanding Benchmark to Probe the Perception Capabilities of Vision-Language Models [83.50100003741628]
  Vision and language models (VLMs) hold immense promise to transform biomedical imaging.<n>We introduce the Massive Multimodal Biomedical Understanding (MMBU) benchmark.<n>It is the largest vision and language benchmark to date, covering 35 submodalities with rich structured metadata.
  arXiv  Detail & Related papers  (2026-06-04T20:24:47Z)
• MedRCube: A Multidimensional Framework for Fine-Grained and In-Depth Evaluation of MLLMs in Medical Imaging [31.5409689069707]
  We propose a paradigm shift toward multidimensional, fine-grained and in-depth evaluation.<n>We benchmark 33 MLLMs, textitLingshu-32B achieve top-tier performance.<n>We introduce a credibility evaluation subset to quantify credibility, uncover a highly significant positive association between shortcut behavior and diagnostic task performance.
  arXiv  Detail & Related papers  (2026-04-15T11:41:20Z)
• Fleming-VL: Towards Universal Medical Visual Reasoning with Multimodal LLMs [7.542510160217106]
  We propose Fleming-VL, a framework for comprehensive medical visual understanding across heterogeneous modalities.<n>Fleming-VL achieves state-of-the-art performance across multiple benchmarks, including medical VQA, video QA, and 3D medical image understanding.
  arXiv  Detail & Related papers  (2025-11-02T12:30:22Z)
• MedKGEval: A Knowledge Graph-Based Multi-Turn Evaluation Framework for Open-Ended Patient Interactions with Clinical LLMs [19.12790150016383]
  We present MedKGEval, a novel multi-turn evaluation framework for clinical large language models.<n>A knowledge graph-driven patient simulation mechanism retrieves relevant medical facts from a curated knowledge graph.<n>A turn-level evaluation framework assesses each model response for clinical appropriateness, factual correctness, and safety.
  arXiv  Detail & Related papers  (2025-10-14T07:22:26Z)
• RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis [56.373297358647655]
  Retrieval-Augmented Diagnosis (RAD) is a novel framework that injects external knowledge into multimodal models directly on downstream tasks.<n>RAD operates through three key mechanisms: retrieval and refinement of disease-centered knowledge from multiple medical sources, a guideline-enhanced contrastive loss transformer, and a dual decoder.
  arXiv  Detail & Related papers  (2025-09-24T10:36:14Z)
• Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning [57.873833577058]
  We build a multimodal dataset enriched with extensive medical knowledge.<n>We then introduce our medical-specialized MLLM: Lingshu.<n>Lingshu undergoes multi-stage training to embed medical expertise and enhance its task-solving capabilities.
  arXiv  Detail & Related papers  (2025-06-08T08:47:30Z)
• LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation [58.25892575437433]
  evaluating large language models (LLMs) in medicine is crucial because medical applications require high accuracy with little room for error.<n>We present LLMEval-Med, a new benchmark covering five core medical areas, including 2,996 questions created from real-world electronic health records and expert-designed clinical scenarios.
  arXiv  Detail & Related papers  (2025-06-04T15:43:14Z)
• A Generative Framework for Bidirectional Image-Report Understanding in Chest Radiography [1.2289361708127877]
  Multi-Stage Adaptive Vision-Language Tuning (MAViLT) is a novel framework designed to enhance multimodal reasoning and generation for vision-based understanding.<n>MAViLT incorporates a clinical gradient-weighted tokenization process and a hierarchical fine-tuning strategy, enabling it to generate accurate radiology reports, synthesize realistic CXRs from text, and answer vision-based clinical questions.<n>We evaluate MAViLT on two benchmark datasets, MIMIC-CXR and Indiana University CXR, achieving state-of-the-art results across all tasks.
  arXiv  Detail & Related papers  (2025-02-09T15:02:57Z)
• Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation [116.87918100031153]
  We propose a Cross-modal clinical Graph Transformer (CGT) for ophthalmic report generation (ORG) CGT injects clinical relation triples into the visual features as prior knowledge to drive the decoding procedure. Experiments on the large-scale FFA-IR benchmark demonstrate that the proposed CGT is able to outperform previous benchmark methods.
  arXiv  Detail & Related papers  (2022-06-04T13:16:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.