Explainable Electrocardiogram Interpretation using Deep Learning-based Semantic Segmentation

Abstract Introduction Accurate electrocardiogram (ECG) waveform delineation, rhythm classification, and median beat generation are interdependent steps whose joint modeling improves consistency for downstream computerized diagnostic tasks. This study aimed to develop a lead-agnostic segmentation model that performs these tasks by segmenting individual leads and aggregating predictions in postprocessing. Methods A DeepLabV3-based neural network was trained to segment ECG leads into 20 waveform and rhythm classes using 1,931 annotated ECGs and 33,093 ECGs with physician-verified diagnostic statements. Postprocessing combined lead-wise predictions to delineate intervals, classify rhythm, and construct median beats. Performance was evaluated on internal (n = 988) and external (n = 1,303) test sets. Median beats were compared with PTB-XL + reference medians from Marquette 12SL and University of Glasgow (Uni-G) using similarity metrics and downstream classification. An interactive web tool (http://segmentation.ecgx.ai) was released to support further research. Results In the external set, delineation for PQ-interval, QRS-duration, and QT-interval had mean errors of -0.9 ± 10.4 ms, 0.2 ± 7.4 ms, and 1.8 ± 16.0 ms. Rhythm classification was performed by assigning class labels to segmented waveform components, with weighted F1 scores of 0.94 for P waves and 0.89 for QRS complexes. Qualitative review showed good alignment with reference beats and differences in beat selection, adjacent beat handling, and QRS identification. Downstream classification performance was equivalent to Marquette 12SL medians but statistically superior to Uni-G medians for 7/10 diagnostic labels. Conclusions This study demonstrates a robust, clinically applicable, vendor- and lead-agnostic deep learning model for ECG analysis, encompassing waveform delineation, rhythm classification, and median beat construction.