UniMedVL: Unifying Medical Multimodal Understanding And Generation Through Observation-Knowledge-Analysis

• URL: http://arxiv.org/abs/2510.15710v2
• Date: Mon, 27 Oct 2025 19:55:52 GMT
• Title: UniMedVL: Unifying Medical Multimodal Understanding And Generation Through Observation-Knowledge-Analysis
• Authors: Junzhi Ning, Wei Li, Cheng Tang, Jiashi Lin, Chenglong Ma, Chaoyang Zhang, Jiyao Liu, Ying Chen, Shujian Gao, Lihao Liu, Yuandong Pu, Huihui Xu, Chenhui Gou, Ziyan Huang, Yi Xin, Qi Qin, Zhongying Deng, Diping Song, Bin Fu, Guang Yang, Yuanfeng Ji, Tianbin Li, Yanzhou Su, Jin Ye, Shixiang Tang, Ming Hu, Junjun He,
• Abstract summary: We introduce UniMedVL, the first medical unified multimodal model for the simultaneous analysis of image understanding and generation tasks.<n>UniMedVL achieves superior performance on five medical image understanding benchmarks, while matching specialized models in generation quality across eight medical imaging modalities.
• Score: 41.864457631668806
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Medical diagnostic applications require models that can process multimodal medical inputs (images, patient histories, lab results) and generate diverse outputs including both textual reports and visual content (annotations, segmentation masks, and images). Despite this need, existing medical AI systems disrupt this unified process: medical image understanding models interpret images but cannot generate visual outputs, while medical image generation models synthesize images but cannot provide textual explanations. This leads to gaps in data representation, feature integration, and task-level multimodal capabilities. To this end, we propose a multi-level framework that draws inspiration from diagnostic workflows through the Observation-Knowledge-Analysis (OKA) paradigm. Specifically, at the observation level, we construct UniMed-5M, a dataset comprising over 5.6M samples that reformat diverse unimodal data into multimodal pairs for foundational observation. At the knowledge level, we propose Progressive Curriculum Learning that systematically introduces medical multimodal knowledge. At the analysis level, we introduce UniMedVL, the first medical unified multimodal model for the simultaneous analysis of image understanding and generation tasks within a single architecture. UniMedVL achieves superior performance on five medical image understanding benchmarks, while matching specialized models in generation quality across eight medical imaging modalities. Crucially, our unified architecture enables bidirectional knowledge sharing: generation tasks enhance visual understanding features, demonstrating that integrating traditionally separate capabilities within a single medical framework unlocks improvements across diverse medical vision-language tasks. Code is available at https://github.com/uni-medical/UniMedVL.

Related papers

• 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)
• MEDMKG: Benchmarking Medical Knowledge Exploitation with Multimodal Knowledge Graph [28.79000907242469]
  We propose MEDMKG, a Medical Multimodal Knowledge Graph that unifies visual and textual medical information through a multi-stage construction pipeline.<n>We evaluate MEDMKG across three tasks under two experimental settings, benchmarking twenty-four baseline methods and four state-of-the-art vision-language backbones on six datasets.<n>Results show that MEDMKG not only improves performance in downstream medical tasks but also offers a strong foundation for developing adaptive and robust strategies for multimodal knowledge integration in medical artificial intelligence.
  arXiv  Detail & Related papers  (2025-05-22T18:41:46Z)
• A Survey of Medical Vision-and-Language Applications and Their Techniques [48.268198631277315]
  Medical vision-and-language models (MVLMs) have attracted substantial interest due to their capability to offer a natural language interface for interpreting complex medical data. Here, we provide a comprehensive overview of MVLMs and the various medical tasks to which they have been applied. We also examine the datasets used for these tasks and compare the performance of different models based on standardized evaluation metrics.
  arXiv  Detail & Related papers  (2024-11-19T03:27:05Z)
• MedViLaM: A multimodal large language model with advanced generalizability and explainability for medical data understanding and generation [40.9095393430871]
  We introduce MedViLaM, a unified vision-language model towards a generalist model for medical data. MedViLaM can flexibly encode and interpret various forms of medical data, including clinical language and imaging. We present instances of zero-shot generalization to new medical concepts and tasks, effective transfer learning across different tasks, and the emergence of zero-shot medical reasoning.
  arXiv  Detail & Related papers  (2024-09-29T12:23:10Z)
• Automated Ensemble Multimodal Machine Learning for Healthcare [52.500923923797835]
  We introduce a multimodal framework, AutoPrognosis-M, that enables the integration of structured clinical (tabular) data and medical imaging using automated machine learning. AutoPrognosis-M incorporates 17 imaging models, including convolutional neural networks and vision transformers, and three distinct multimodal fusion strategies.
  arXiv  Detail & Related papers  (2024-07-25T17:46:38Z)
• Medical Vision-Language Pre-Training for Brain Abnormalities [96.1408455065347]
  We show how to automatically collect medical image-text aligned data for pretraining from public resources such as PubMed. In particular, we present a pipeline that streamlines the pre-training process by initially collecting a large brain image-text dataset. We also investigate the unique challenge of mapping subfigures to subcaptions in the medical domain.
  arXiv  Detail & Related papers  (2024-04-27T05:03:42Z)
• AliFuse: Aligning and Fusing Multi-modal Medical Data for Computer-Aided Diagnosis [1.64647940449869]
  We propose a transformer-based framework, called Alifuse, for aligning and fusing multimodal medical data.<n>We convert medical images and both unstructured and structured clinical records into vision and language tokens.<n>We apply Alifuse to classify Alzheimer's disease, achieving state-of-the-art performance on five public datasets and outperforming eight baselines.
  arXiv  Detail & Related papers  (2024-01-02T07:28:21Z)
• LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching [59.01894976615714]
  We introduce LVM-Med, the first family of deep networks trained on large-scale medical datasets. We have collected approximately 1.3 million medical images from 55 publicly available datasets. LVM-Med empirically outperforms a number of state-of-the-art supervised, self-supervised, and foundation models.
  arXiv  Detail & Related papers  (2023-06-20T22:21:34Z)
• Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training [5.119201893752376]
  We propose Medical Vision Language Learner (MedViLL) which adopts a Transformer-based architecture combined with a novel multimodal attention masking scheme. We empirically demonstrate the superior downstream task performance of MedViLL against various baselines including task-specific architectures.
  arXiv  Detail & Related papers  (2021-05-24T15:14:09Z)

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.