Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.03733 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913976890163200 |
|---|---|
| author | Li, Wenjie Zhang, Yujie Sun, Haoran Li, Yueqi Zhang, Fanrui Xu, Mengzhe Clausich, Victoria Borja Mellin, Sade Yang, Renhao Wang, Chenrun Wang, Jethro Zih-Shuo Yao, Shiyi Li, Gen Xu, Yidong Wang, Hanyu Huang, Yilin Wang, Angela Lin Shi, Chen Zhang, Yin Guo, Jianan Yang, Luqi Li, Renxuan Xu, Yang Liu, Jiawei Zhang, Yao Liu, Lei SanRomán, Carlos Gutiérrez Wang, Lei |
| author_facet | Li, Wenjie Zhang, Yujie Sun, Haoran Li, Yueqi Zhang, Fanrui Xu, Mengzhe Clausich, Victoria Borja Mellin, Sade Yang, Renhao Wang, Chenrun Wang, Jethro Zih-Shuo Yao, Shiyi Li, Gen Xu, Yidong Wang, Hanyu Huang, Yilin Wang, Angela Lin Shi, Chen Zhang, Yin Guo, Jianan Yang, Luqi Li, Renxuan Xu, Yang Liu, Jiawei Zhang, Yao Liu, Lei SanRomán, Carlos Gutiérrez Wang, Lei |
| contents | Chest X-ray (CXR) imaging is one of the most widely used diagnostic modalities in clinical practice, encompassing a broad spectrum of diagnostic tasks. Recent advancements have seen the extensive application of reasoning-based multimodal large language models (MLLMs) in medical imaging to enhance diagnostic efficiency and interpretability. However, existing multimodal models predominantly rely on "one-time" diagnostic approaches, lacking verifiable supervision of the reasoning process. This leads to challenges in multi-task CXR diagnosis, including lengthy reasoning, sparse rewards, and frequent hallucinations. To address these issues, we propose CX-Mind, the first generative model to achieve interleaved "think-answer" reasoning for CXR tasks, driven by curriculum-based reinforcement learning and verifiable process rewards (CuRL-VPR). Specifically, we constructed an instruction-tuning dataset, CX-Set, comprising 708,473 images and 2,619,148 samples, and generated 42,828 high-quality interleaved reasoning data points supervised by clinical reports. Optimization was conducted in two stages under the Group Relative Policy Optimization framework: initially stabilizing basic reasoning with closed-domain tasks, followed by transfer to open-domain diagnostics, incorporating rule-based conditional process rewards to bypass the need for pretrained reward models. Extensive experimental results demonstrate that CX-Mind significantly outperforms existing medical and general-domain MLLMs in visual understanding, text generation, and spatiotemporal alignment, achieving an average performance improvement of 25.1% over comparable CXR-specific models. On real-world clinical dataset (Rui-CXR), CX-Mind achieves a mean recall@1 across 14 diseases that substantially surpasses the second-best results, with multi-center expert evaluations further confirming its clinical utility across multiple dimensions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_03733 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CX-Mind: A Pioneering Multimodal Large Language Model for Interleaved Reasoning in Chest X-ray via Curriculum-Guided Reinforcement Learning Li, Wenjie Zhang, Yujie Sun, Haoran Li, Yueqi Zhang, Fanrui Xu, Mengzhe Clausich, Victoria Borja Mellin, Sade Yang, Renhao Wang, Chenrun Wang, Jethro Zih-Shuo Yao, Shiyi Li, Gen Xu, Yidong Wang, Hanyu Huang, Yilin Wang, Angela Lin Shi, Chen Zhang, Yin Guo, Jianan Yang, Luqi Li, Renxuan Xu, Yang Liu, Jiawei Zhang, Yao Liu, Lei SanRomán, Carlos Gutiérrez Wang, Lei Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Chest X-ray (CXR) imaging is one of the most widely used diagnostic modalities in clinical practice, encompassing a broad spectrum of diagnostic tasks. Recent advancements have seen the extensive application of reasoning-based multimodal large language models (MLLMs) in medical imaging to enhance diagnostic efficiency and interpretability. However, existing multimodal models predominantly rely on "one-time" diagnostic approaches, lacking verifiable supervision of the reasoning process. This leads to challenges in multi-task CXR diagnosis, including lengthy reasoning, sparse rewards, and frequent hallucinations. To address these issues, we propose CX-Mind, the first generative model to achieve interleaved "think-answer" reasoning for CXR tasks, driven by curriculum-based reinforcement learning and verifiable process rewards (CuRL-VPR). Specifically, we constructed an instruction-tuning dataset, CX-Set, comprising 708,473 images and 2,619,148 samples, and generated 42,828 high-quality interleaved reasoning data points supervised by clinical reports. Optimization was conducted in two stages under the Group Relative Policy Optimization framework: initially stabilizing basic reasoning with closed-domain tasks, followed by transfer to open-domain diagnostics, incorporating rule-based conditional process rewards to bypass the need for pretrained reward models. Extensive experimental results demonstrate that CX-Mind significantly outperforms existing medical and general-domain MLLMs in visual understanding, text generation, and spatiotemporal alignment, achieving an average performance improvement of 25.1% over comparable CXR-specific models. On real-world clinical dataset (Rui-CXR), CX-Mind achieves a mean recall@1 across 14 diseases that substantially surpasses the second-best results, with multi-center expert evaluations further confirming its clinical utility across multiple dimensions. |
| title | CX-Mind: A Pioneering Multimodal Large Language Model for Interleaved Reasoning in Chest X-ray via Curriculum-Guided Reinforcement Learning |
| topic | Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.03733 |