发表机构
INSA-Lyon, Universite Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, CREATIS UMR 5220, U1294; Institut Universitaire de France (IUF); University of Sherbrooke; Huazhong University of Science and Technology; Sunnybrook Research Institute, University of Toronto; Imperial College London; University College London; Fudan University; Medical University of Graz; Graz University of Technology; Universidad de Zaragoza; Instituto de Investigación Sanitaria de Aragón (IIS Aragón); Centre Hospitalier Annecy Genevois; Hôpital Universitaire Cardiologique Louis Pradel（里昂国立应用科学学院、里昂第一大学克洛德·贝尔纳大学、圣艾蒂安大学、法国国家科学研究中心、法国国家健康与医学研究院、CREATIS联合研究机构; 法兰西大学研究院; 谢布鲁克大学; 华中科技大学; 多伦多大学桑尼布鲁克研究所; 伦敦帝国理工学院; 伦敦大学学院; 复旦大学; 格拉茨医科大学; 格拉茨技术大学; 萨拉戈萨大学; 阿拉贡卫生研究所; 阿讷西日内瓦中心医院; 路易·普拉德尔大学心脏病医院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文介绍MYOSAIQ挑战赛，整合439例多中心CMR数据，6支队伍参赛，对比发现基于UNet的技术在LGE MR分割上优于基础模型，但梗死区域分割仍需改进。
AI 中文摘要
钆延迟增强（LGE）心脏磁共振（MR）成像是评估心肌梗死（MI）病灶的首选模态。目前，心肌梗死体积量化在临床实践中并未常规开展。众多深度学习（DL）方法已被开发用于自动化分割心肌和梗死区域，但多数研究依赖相对较小的数据集，这些数据集通常会经过预处理步骤以标准化图像，并聚焦于再灌注治疗后心肌梗死的特定阶段。这些限制阻碍了可在不同场景下通用的模型开发，因此难以适用于常规临床应用。为推进心肌梗死量化通用学习的研究并建立基准，本文呈现了“自动化梗死量化的心肌分割（MYOSAIQ）”挑战赛的相关成果。该挑战赛搭建的数据集整合了两项多中心临床试验的439例心脏磁共振（CMR）体积数据，包含急性心肌梗死后急性期和慢性期的代表性数据，数据来自16个中心使用3个不同厂商的MRI扫描仪采集。挑战赛结束时共有6支参赛队伍，采用了各类基线模型、数据增强技术和置信度策略。为提升本研究的重要性，我们将参赛队伍的结果与微调后的基础模型结果进行了比较。结果表明，设计良好的基于UNet的技术在LGE MR分割任务上的表现优于全自动化基础模型。尽管最优方法能在多种场景下高质量且稳定地勾勒出左心室和心肌，但在准确分割梗死区域方面仍有改进空间。
英文摘要
Late gadolinium enhancement (LGE) cardiac magnetic resonance (MR) imaging is the modality of choice to assess myocardial infarction (MI) lesions. Nowadays MI volume quantification is not performed routinely in clinical practice. Numerous deep learning (DL) methods have been developed to automate the segmentation of the myocardium and infarct regions. However, most studies rely on relatively small datasets which typically undergo pre-processing steps to standardize images and focus on a specific phase of myocardial infarction following reperfusion therapy. These limitations have impeded the development of models that are generalizable across diverse conditions and thus suitable for routine clinical use. To advance research and establish benchmarks in generalizable learning for myocardial infarct quantification, this paper presents findings from the Myocardial Segmentation with Automated Infarct Quantification (MYOSAIQ) challenge. The dataset set up for the challenge combines 439 CMR volumes from two multicenter clinical trials, with representative data acquired in acute and chronic phases after acute MI. Data were acquired in 16 centers using MRI scanners from three different vendors. Six teams participated until the end of the challenge, employing various baseline models, data augmentation techniques, and confidence strategies. To enhance the significance of this study, we compare the challengers' results with those of fine-tuned foundation models. Our results indicate that well-designed UNet-based techniques outperform fully automatic foundation models for LGE MR segmentation. While the best methods achieve high-quality and stable delineations of the left ventricle and myocardium under various conditions, they remain improvable in accurately segmenting infarct regions.
CommentsAccepted for publication at the Journal of Machine Learning for Biomedical Imaging (MELBA) https://melba-journal.org/2026:032
Journal refMachine.Learning.for.Biomedical.Imaging. 2026 (2026)
DOI：10.59275/j.melba.2026-e93b
