Publications by authors named "Zhoutong Li"
Bootstrap each lead's latent: A novel method for self-supervised learning of multilead electrocardiograms.
Comput Methods Programs Biomed
December 2024
Article Synopsis
- Electrocardiograms (ECGs) are vital for diagnosing cardiovascular diseases, but training deep learning models for automated detection normally depends on expensive and time-consuming manual labeling.* -
- The proposed BELL method (bootstrap each lead's latent) enhances model performance by using self-supervised learning to leverage unlabeled ECG data, minimizing the reliance on labeled data during training.* -
- BELL outperforms previous models, showing improved performance in downstream tasks with limited training data and demonstrating adaptability to uncurated real-world ECG data, reducing the need for manual cardiologist labels.*
Most of the existing multi-lead electrocardiogram (ECG) detection methods are based on all 12 leads, which undoubtedly results in a large amount of calculation and is not suitable for the application in portable ECG detection systems. Moreover, the influence of different lead and heartbeat segment lengths on the detection is not clear. In this paper, a novel Genetic Algorithm-based ECG Leads and Segment Length Optimization (GA-LSLO) framework is proposed, aiming to automatically select the appropriate leads and input ECG length to achieve optimized cardiovascular disease detection.
View Article and Find Full Text PDF