Toward Modality- and Sampling-Universal Learning Strategies for Accelerating Cardiovascular Imaging: Summary of the CMRxRecon2024 Challenge

作者：Fanwen Wang, Zi Wang, Yan Li, Jun Lyu, Chen Qin, Shuo Wang, Kunyuan Guo, Mengting Sun, Mingkai Huang, Haoyu Zhang, Michael Tänzer, Q Li, Xinran Chen, Jiahao Huang, Yinzhe Wu, Haosen Zhang, Kian Anvari Hamedani, Y. F. Lyu, Longyu Sun, Qing Li, Tianxing He, Lizhen Lan, Qiong Yao, Ziqiang Xu, Bingyu Xin, Dimitris Metaxas, Narges Razizadeh, Shahabedin Nabavi, George Yiasemis, Jonas Teuwen, Zhenxi Zhang, Sha Wang, Chi Zhang, Daniel B. Ennis, Zhihao Xue, Chenxi Hu, Ruru Xu, İlkay Öksüz, Donghang Lyu, Y.X. Huang, Xin Guo, Ruqian Hao, Jaykumar Patel, Guanke Cai, Binghua Chen, Yajing Zhang, Sha Hua, Zhensen Chen, Qi Dou, Xiahai Zhuang, Qian Tao, Wenjia Bai, Jing Qin, He Wang, Claudia Prieto, Michael Markl, Alistair A. Young, Hao Li, Xihong Hu, Lian‐Ming Wu, Xiaobo Qu, Guang Yang, Chengyan Wang · 发表于：IEEE Transactions on Medical Imaging · 年份：2025 · DOI：10.1109/tmi.2025.3641610 · 被引用次数：1 · 研究领域：Cardiac Imaging and Diagnostics、Advanced MRI Techniques and Applications、Cardiovascular Function and Risk Factors

Cardiovascular health is vital to human well-being, and cardiac magnetic resonance (CMR) imaging is considered the clinical reference standard for diagnosing cardiovascular disease. However, its adoption is hindered by long scan times, complex contrasts, and inconsistent quality. While deep learning methods perform well on specific CMR imaging sequences, they often fail to generalize across modalities and sampling schemes. The lack of benchmarks for high-quality, fast CMR image reconstruction further limits technology comparison and adoption. The CMRxRecon2024 challenge, attracting over 200 teams from 18 countries, addressed these issues with two tasks: generalization to unseen modalities and robustness to diverse undersampling patterns. We introduced the largest public multi-modality CMR raw dataset, an open benchmarking platform, and shared code. Analysis of the best-performing solutions revealed that prompt-based adaptation and enhanced physics-driven consistency enabled strong cross-scenario performance. These findings establish principles for generalizable reconstruction models and advance clinically translatable AI in cardiovascular imaging.