解决心脏影像重建通用性难题，提升多模态与采样下的成像速度与质量。
Towards Modality- and Sampling-Universal Learning Strategies for Accelerating Cardiovascular Imaging: Summary of the CMRxRecon2024 Challenge
- 采用提示调优与物理一致性增强，实现跨模态和采样方案的泛化重建。
- 在200+团队参与的挑战赛中，最佳模型在未见模态上仍保持高重建精度。
- 公开最大规模多模态心脏MRI原始数据集，推动临床AI可落地应用。
心血管健康关乎人类福祉，心脏磁共振（CMR）成像是诊断心血管疾病的临床金标准。然而，其应用受限于扫描时间长、对比方式复杂及图像质量不一。尽管深度学习在特定CMR序列上表现优异，但跨模态和采样方案的泛化能力差。缺乏高质量、快速重建的基准评测体系也阻碍了技术比较与临床采纳。CMRxRecon2024挑战赛汇聚来自18个国家的200多个团队，设立两项任务：对未见模态的泛化能力与对多样化欠采样模式的鲁棒性。研究发布了目前最大的公共多模态CMR原始数据集，构建开放评测平台并开源代码。对最优解法分析表明，基于提示的自适应策略与增强的物理驱动一致性，显著提升了跨场景性能。这些发现为可泛化的重建模型提供了设计原则，推动了心血管影像中临床可转化的人工智能发展。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。