Multi-scale Cross-restoration Framework for Electrocardiogram Anomaly Detection

TL;DR

This paper presents a novel multi-scale cross-restoration framework employing a two-branch autoencoder to detect and localize ECG anomalies by analyzing both global and local features, achieving state-of-the-art results on new and existing datasets.

Contribution

It introduces a multi-scale cross-restoration autoencoder framework that mimics cardiologists' diagnostic process for ECG anomaly detection and localization, with a new benchmark dataset.

Findings

State-of-the-art performance on ECG anomaly detection

Effective localization of anomalies at signal point level

Robust detection across diverse ECG datasets

Abstract

Electrocardiogram (ECG) is a widely used diagnostic tool for detecting heart conditions. Rare cardiac diseases may be underdiagnosed using traditional ECG analysis, considering that no training dataset can exhaust all possible cardiac disorders. This paper proposes using anomaly detection to identify any unhealthy status, with normal ECGs solely for training. However, detecting anomalies in ECG can be challenging due to significant inter-individual differences and anomalies present in both global rhythm and local morphology. To address this challenge, this paper introduces a novel multi-scale cross-restoration framework for ECG anomaly detection and localization that considers both local and global ECG characteristics. The proposed framework employs a two-branch autoencoder to facilitate multi-scale feature learning through a masking and restoration process, with one branch focusing on global features from the entire ECG and the other on local features from heartbeat-level details, mimicking the diagnostic process of cardiologists. Anomalies are identified by their high restoration errors. To evaluate the performance on a large number of individuals, this paper introduces a new challenging benchmark with signal point-level ground truths annotated by experienced cardiologists. The proposed method demonstrates state-of-the-art performance on this benchmark and two other well-known ECG datasets. The benchmark dataset and source code are available at: \url{https://github.com/MediaBrain-SJTU/ECGAD}