BrainMVP: Multi-modal Vision Pre-training for Medical Image Analysis[CVPR2025 Highlight]

Shaohao Rui, Lingzhi Chen, Zhenyu Tang, Lilong Wang, Mianxin Liu, Shaoting Zhang, Xiaosong Wang

We introduce the first multi-modal vision pre-training method (BrainMVP) for missing modality medical data. We demonstrate the superior performance and the enhanced generalizability of our BrainMVP pre-trained models on ten public segmentation and classification benchmarks compared to state-of-the-art methods.

Github

MedCCO: Improving Medical Reasoning with Curriculum-Aware Reinforcement Learning[NeurIPS Under Review]

Shaohao Rui, Kaitao Chen, Weijie Ma, Xiaosong Wang

We introduce MedCCO, the first multimodal reinforcement learning framework for medical VQA that unifies close-ended and open-ended data within a curriculum-driven fine-tuning paradigm. MedCCO significantly improves clinical reasoning and generalization across eight benchmarks, achieving 11.4% in-domain and 5.7% out-of-domain performance gains over prior methods.

Github

CardioCoT: Hierarchical Reasoning for Multimodal Survival Analysis[arXiv]

Shaohao Rui, Haoyang Su, Jinyi Xiang, Lian-Ming Wu, and Xiaosong Wang

We propose CardioCoT, a hierarchical reasoning-enhanced survival analysis framework for MACE recurrence risk prediction in AMI patients, leveraging postoperative cardiac MRI and clinical notes. CardioCoT integrates evidence-augmented reasoning with imaging data, achieving superior predictive performance and interpretability to support precision clinical decision-making.

Github