A Multilevel Metric Fusion Framework for Few-Shot Electrocardiogram Classification

Due to insufficient samples in rare arrhythmia classes, current research in electrocardiogram (ECG) classification has reported poor performance in rare arrhythmia classes and difficulties in promptly generalizing to novel, unseen classes. This article introduces a novel multilevel metric fusion framework specifically designed for few-shot ECG classification. The framework aims to extract multilevel deep local descriptors and learn the intricate relationships between samples across different levels, thereby enhancing the few-shot ECG classification capability. In the proposed method, the episodic training mechanism based on N-way K-shot task is introduced to effectively train deep neural networks with limited samples. Then, a unique multilevel metric fusion framework is developed for similarity learning, which jointly utilizes heartbeat-level and segment-level features for metric learning. Furthermore, the multilevel metric fusion module integrates weighted fusion of heartbeat-level and segment-level scores along the branch dimension, forming a global decision similarity. The proposed method was evaluated on a few-shot ECG database, demonstrating remarkable performance with average accuracies of 72.74%, 69.81%, and 49.84% for five-way ten-shot, five-shot, and one-shot scenarios, respectively. These results significantly surpass existing methods, highlighting the effectiveness of the proposed approach. This study presents a straightforward yet highly effective solution for multilead ECG classification, particularly suitable for few-shot scenarios. Furthermore, the proposed multilevel metric fusion module effectively leverages multilevel features, demonstrating its potential for improved generalization and accuracy in ECG classification tasks. This is the first study to achieve wide-range class classification in few-shot scenarios without relying on auxiliary techniques such as transfer learning or pretraining, and demonstrating important impact to clinical applications.