YOLO-ResTinyECG: ECG-based lightweight embedded AI arrhythmia small object detector with pruning methods

Objective

This study presents a YOLO-ResTinyECG, a novel model for small object detection in electrocardiogram (ECG) images, emphasizing longer time-window lengths for improving the throughput of arrhythmia detection. Methods: The proposed ResTinyECG backbone consists of four-stage Res-blocks (2/4/3/2) with input ECG image sizes of 320 × 320 × 1 pixels and 160 × 160 × 1 pixels, with a significant parameter reduction of around 20 %/95 %/74 % compared to existing backbones like Shufflenet-v2/CSPDarknet53-tiny and the latest YOLOv7-tiny structure. Moreover, this study applied magnitude-based filter pruning and dependency graph (DepGraph) pruning for parameter optimization. The ECG images undergo processing with time-window lengths of 5/10/15/20 s, accompanied by min–max normalization, and weighted loss is applied for class balance during learning, and non-maximum suppression with edge removal is used to compute and select the final output bounding boxes of ECG heartbeats. Experiments: Experiments conducted on the PhysioNet MIT-BIH arrhythmia ECG database focus on nine classes, including normal (N), atrial premature beat (A), ventricular premature beat (V), left bundle branch block (L), right bundle branch block (R), fusion of ventricular beat (FVN), paced beat (P), fusion of paced and normal beat (FPN), and others (remaining heartbeats). Results: The proposed ResTinyECG-320 exhibits impressive mean Average Precision (mAP) scores of 94.76 %/94.85 %/93.96 %/87.12 % in 6-class detection and 92.35 %/91.96 %/90.58 %/83.34 % in 9-class detection across different time-window lengths. The model demonstrates only a marginal 7 %∼9% decrease in performance when utilizing longer time-window lengths. After applying magnitude-based filter pruning, ResTinyECG can be reduced to a minimal 0.1 million parameters. Furthermore, ResTinyECG-160 achieves a competitive mAP of 93.92 % in 6-class detection and a faster processing speed of 100.6 ECG segments per second (SPS) on a PC compared to Shufflenet-v2 (77.3 SPS). In conclusion, YOLO-ResTinyECG surpasses existing backbones, exhibiting superior mAP in both 6/9-class detection scenarios, and its deployment on an embedded AI platform validates its real-time detection capabilities.