用于心脏MRI和ECG联合表示的全局和局部对比学习
Global and Local Contrastive Learning for Joint Representations from Cardiac MRI and ECG
- Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM) and TUM University Hospital, Munich, Germany（人工智能在医疗与医学中的研究中心，技术大学慕尼黑（TUM）及慕尼黑技术大学医院）
- School of Medicine, Klinikum rechts der Isar, TUM, Germany（医学院，右岸克里克医院，TUM，德国）
- Department of Computing, Imperial College London, UK（计算学院，伦敦帝国学院，英国）
- Munich Center for Machine Learning (MCML), Munich, Germany（慕尼黑机器学习中心（MCML），慕尼黑，德国）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
PTACL通过结合心脏MRI的时空信息提升ECG表示，实现患者级和时间级对比学习，提高心脏表型检索和功能参数预测的性能。
AI中文摘要：
心电图（ECG）是一种广泛使用的、成本效益高的工具，用于检测心脏的电异常。然而，它不能直接测量功能参数，如心室容积和射血分数，这些参数对评估心脏功能至关重要。心脏磁共振成像（CMR）是这些测量的金标准，提供详细的结构和功能信息，但成本高且可及性低。为弥合这一差距，我们提出了PTACL（患者和时间对齐对比学习），一种多模态对比学习框架，通过整合来自CMR的时空信息来增强ECG表示。PTACL使用全局患者级对比损失和局部时间级对比损失。全局损失通过将来自同一患者的ECG和CMR嵌入拉近，同时将不同患者的嵌入推远，对齐患者级表示。局部损失通过对比编码的ECG段与对应的编码CMR帧，强制在每个患者内部进行精细的时间对齐。这种方法通过超越仅靠全局对齐的对比学习，使ECG表示丰富化，获得诊断信息，同时在模态之间转移更多的见解。我们在英国生物银行中27,951名受试者的配对ECG-CMR数据上评估了PTACL。与基线方法相比，PTACL在两个临床相关任务中表现更好：（1）检索具有相似心脏表型的患者；（2）预测CMR衍生的心脏功能参数，如心室容积和射血分数。我们的结果强调了PTACL在利用ECG进行非侵入性心脏诊断中的潜力。代码可在：https://github.com/alsalivan/ecgcmr 上获得。
英文摘要：
An electrocardiogram (ECG) is a widely used, cost-effective tool for detecting electrical abnormalities in the heart. However, it cannot directly measure functional parameters, such as ventricular volumes and ejection fraction, which are crucial for assessing cardiac function. Cardiac magnetic resonance (CMR) is the gold standard for these measurements, providing detailed structural and functional insights, but is expensive and less accessible. To bridge this gap, we propose PTACL (Patient and Temporal Alignment Contrastive Learning), a multimodal contrastive learning framework that enhances ECG representations by integrating spatio-temporal information from CMR. PTACL uses global patient-level contrastive loss and local temporal-level contrastive loss. The global loss aligns patient-level representations by pulling ECG and CMR embeddings from the same patient closer together, while pushing apart embeddings from different patients. Local loss enforces fine-grained temporal alignment within each patient by contrasting encoded ECG segments with corresponding encoded CMR frames. This approach enriches ECG representations with diagnostic information beyond electrical activity and transfers more insights between modalities than global alignment alone, all without introducing new learnable weights. We evaluate PTACL on paired ECG-CMR data from 27,951 subjects in the UK Biobank. Compared to baseline approaches, PTACL achieves better performance in two clinically relevant tasks: (1) retrieving patients with similar cardiac phenotypes and (2) predicting CMR-derived cardiac function parameters, such as ventricular volumes and ejection fraction. Our results highlight the potential of PTACL to enhance non-invasive cardiac diagnostics using ECG. The code is available at: https://github.com/alsalivan/ecgcmr
