Temporal and spatial self supervised learning methods for electrocardiograms.

Journal: Scientific reports
Published Date:

Abstract

The limited availability of labeled ECG data restricts the application of supervised deep learning methods in ECG detection. Although existing self-supervised learning approaches have been applied to ECG analysis, they are predominantly image-based, which limits their effectiveness. To address these limitations and provide novel insights, we propose a Temporal-Spatial Self-Supervised Learning (TSSL) method specifically designed for ECG detection. TSSL leverages the intrinsic temporal and spatial characteristics of ECG signals to enhance feature representation. Temporally, ECG signals retain consistent identity information over time, enabling the model to generate stable representations for the same individual across different time points while isolating representations of different leads to preserve their unique features. Spatially, ECG signals from various leads capture the heart's activity from different perspectives, revealing both commonalities and distinct patterns. TSSL captures these correlations by maintaining consistency in the relationships between signals and their representations across different leads. Experimental results on the CPSC2018, Chapman, and PTB-XL databases demonstrate that TSSL introduces new capabilities by effectively utilizing temporal and spatial information, achieving superior performance compared to existing methods and approaching the performance of full-label training with only 10% of the labeled data. This highlights TSSL's ability to provide deeper insights and enhanced feature extraction beyond mere performance improvements. We make our code publicly available on https://github.com/cwp9731/temporal-spatial-self-supervised-learning.

Authors

  • Wenping Chen
    From the Department of Radiology, Affiliated Nanjing Drum Tower Hospital of Nanjing University Medical School, Nanjing, China (D.M., W.C., H.Y., J.L., K.Y., H.L., Z.Q., B.Z.); Keya Medical, Shenzhen, China (J.B., H.Y.Y., J.Z., Y.Y.); Medical School of Nanjing University, Nanjing, China (K.H.); National Institutes of Healthcare Data Science at Nanjing University, Nanjing, China (K.H.); University of South Carolina School of Medicine-Columbia, Columbia, SC (H.W.M.); Division of Cardiovascular Imaging, Medical University of South Carolina, Charleston, SC (U.J.S.); Institute of Brain Science, Nanjing University, Nanjing 210008, China (B.Z.).
  • Huibin Wang
    Shanghai Frontiers Science Center of Molecule Intelligent Syntheses, School of Computer Science and Technology, East China Normal University, Shanghai 200062, China.
  • Lili Zhang
    Pharmaceutics Department, Institute of Medicinal Biotechnology, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, 100050, PR China.
  • Min Zhang
    Department of Infectious Disease, The Second Xiangya Hospital of Central South University, Changsha, China.