通过稀疏二维心脏MR图像进行全心3D+T表示学习
Whole Heart 3D+T Representation Learning Through Sparse 2D Cardiac MR Images
AI总结：
本文提出一种基于掩码成像建模的全心自监督学习框架，从稀疏二维心脏MR图像中学习紧凑的3D+T心脏表示，在心脏表型预测与多平面分割任务中优于基线方法。
摘要：
心脏磁共振（CMR）成像是评估心脏形态与功能的金标准。通常，为了进行全面的心脏评估，需要采集覆盖短轴（SA）和2/3/4腔长轴（LA）视图的多视图CMR堆叠。然而，如何高效地简化复杂、高维的3D+T CMR数据，并提炼出紧凑且连贯的表示仍然是一个挑战。在本工作中，我们引入了一个全心自监督学习框架，该框架利用掩码成像建模来自动发现整个心脏堆叠中空间补丁与时间补丁之间的相关性。这一过程有助于生成有意义且聚类良好的心脏表示，而无需依赖传统上所需且通常成本高昂的标注数据。学习到的心脏表示可以直接用于各种下游任务。此外，我们的方法表现出显著的鲁棒性，即使在缺失或有缺陷的某些CMR平面情况下，也能确保表示的一致性。我们在来自UK BioBank的14,000个未标注CMR数据上训练模型，并在1,000个标注数据上进行评估。所提出的方法在需要全面3D+T心脏信息的任务中表现出优于基线的性能，例如心脏表型（射血分数和心室容积）预测以及多平面/多帧CMR分割，突显了其在提取解剖学和病理学相关综合心脏特征方面的有效性。
英文摘要：
Cardiac Magnetic Resonance (CMR) imaging serves as the gold-standard for evaluating cardiac morphology and function. Typically, a multi-view CMR stack, covering short-axis (SA) and 2/3/4-chamber long-axis (LA) views, is acquired for a thorough cardiac assessment. However, efficiently streamlining the complex, high-dimensional 3D+T CMR data and distilling compact, coherent representation remains a challenge. In this work, we introduce a whole-heart self-supervised learning framework that utilizes masked imaging modeling to automatically uncover the correlations between spatial and temporal patches throughout the cardiac stacks. This process facilitates the generation of meaningful and well-clustered heart representations without relying on the traditionally required, and often costly, labeled data. The learned heart representation can be directly used for various downstream tasks. Furthermore, our method demonstrates remarkable robustness, ensuring consistent representations even when certain CMR planes are missing/flawed. We train our model on 14,000 unlabeled CMR data from UK BioBank and evaluate it on 1,000 annotated data. The proposed method demonstrates superior performance to baselines in tasks that demand comprehensive 3D+T cardiac information, e.g. cardiac phenotype (ejection fraction and ventricle volume) prediction and multi-plane/multi-frame CMR segmentation, highlighting its effectiveness in extracting comprehensive cardiac features that are both anatomically and pathologically relevant.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
