发表机构
Maastricht University; University Hospital Münster; Eindhoven University of Technology（马斯特里赫特大学; 明斯特大学医院; 埃因霍温理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对CMR-Multi挑战，微调CineMA并组合冻结CMR基础模型，实现多视图CMR分割与直接LVEF估算，验证了基础模型适配多视图CMR分析的有效性。
AI 中文摘要
基础模型在心脏MRI（CMR）中展现出强大的迁移能力，但其在异质性多视图、多序列CMR分析中的有效性仍不明确。本研究针对通用多序列、多中心、多视图CMR分割（CMR-Multi）挑战，探索微调及组合不同CMR基础模型的有效性：对CineMA进行微调，用于短轴、两腔、四腔视图的电影MRI及钆延迟强化（LGE）分割；对于直接左心室射血分数（LVEF）估算，采用两个近期的冻结CMR基础模型提取嵌入向量，再通过基于注意力的多实例学习将其组合用于LVEF回归。在挑战验证集上，电影MRI分割在短轴、两腔、四腔视图的Dice分数分别为0.862、0.883、0.902；LGE分割在各视图的Dice分数介于0.621至0.846之间；直接LVEF回归模型的平均绝对误差（MAE）为4.96个百分点，皮尔逊相关系数为0.91。结果表明，基础模型可有效适配并组合用于多视图CMR分析，但精准的LGE瘢痕分割仍是一项具有挑战性的任务。
英文摘要
Foundation models have shown strong transferability in cardiac MRI (CMR), but their effectiveness for heterogeneous multi-view and multi-sequence CMR analysis remains unclear. In this work, we explore the effectiveness of fine-tuning and combining different CMR foundation models for the Universal Multi-Sequence, Multi-Center and Multi-View CMR Segmentation (CMR-Multi) Challenge. CineMA was fine-tuned for cine and late gadolinium enhancement (LGE) segmentation across short-axis and long-axis views. For direct left-ventricular ejection fraction (LVEF) estimation, we used two recent frozen CMR foundation models to extract embedding vectors that were then combined using attention-based multiple-instance learning for LVEF regression. In the challenge validation set, cine segmentation achieved Dice scores of 0.862, 0.883, and 0.902 for short-axis, two-chamber and four-chamber cine MRI, respectively. LGE segmentation achieved Dice scores between 0.621 and 0.846 across views. The direct LVEF regression model achieved an MAE of 4.96 percentage points and a Pearson correlation of 0.91. These results indicate that foundation models can be effectively adapted and combined for multi-view CMR analysis, while accurate LGE scar segmentation remains a challenging task.
