SemiSegECG: A Multi-Dataset Benchmark for Semi-Supervised Semantic Segmentation in ECG Delineation

TL;DR

SemiSegECG introduces a comprehensive benchmark for semi-supervised ECG delineation, combining multiple datasets, algorithms, and architectures to advance research in this critical clinical task.

Contribution

It is the first systematic benchmark for semi-supervised ECG delineation, integrating datasets, algorithms, and evaluation protocols to foster future research.

Findings

Transformers outperform convolutional networks in semi-supervised ECG delineation.

The benchmark supports in-domain and cross-domain evaluation.

Proposed training strategies improve semi-supervised segmentation performance.

Abstract

Electrocardiogram (ECG) delineation, the segmentation of meaningful waveform features, is critical for clinical diagnosis. Despite recent advances using deep learning, progress has been limited by the scarcity of publicly available annotated datasets. Semi-supervised learning presents a promising solution by leveraging abundant unlabeled ECG data. In this study, we present SemiSegECG, the first systematic benchmark for semi-supervised semantic segmentation (SemiSeg) in ECG delineation. We curated and unified multiple public datasets, including previously underused sources, to support robust and diverse evaluation. We adopted five representative SemiSeg algorithms from computer vision, implemented them on two different architectures: the convolutional network and the transformer, and evaluated them in two different settings: in-domain and cross-domain. Additionally, we propose ECG-specific training configurations and augmentation strategies and introduce a standardized evaluation framework. Our results show that the transformer outperforms the convolutional network in semi-supervised ECG delineation. We anticipate that SemiSegECG will serve as a foundation for advancing semi-supervised ECG delineation methods and will facilitate further research in this domain.