Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Pathology-Aware Multi-View Contrastive Learning for Patient-Independent ECG Reconstruction

Youssef Youssef, Jitin Singla

Abstract

Reconstructing a 12-lead electrocardiogram (ECG) from a reduced lead set is an ill-posed inverse problem due to anatomical variability. Standard deep learning methods often ignore underlying cardiac pathology losing vital morphology in precordial leads. We propose Pathology-Aware Multi-View Contrastive Learning, a framework that regularizes the latent space through a pathological manifold. Our architecture integrates high-fidelity time-domain waveforms with pathology-aware embeddings learned via supervised contrastive alignment. By maximizing mutual information between latent representations and clinical labels, the framework learns to filter anatomical "nuisance" variables. On the PTB-XL dataset, our method achieves approx. 76\% reduction in RMSE compared to state-of-the-art model in patient-independent setting. Cross-dataset evaluation on the PTB Diagnostic Database confirms superior generalization, bridging the gap between hardware portability and diagnostic-grade reconstruction.

Pathology-Aware Multi-View Contrastive Learning for Patient-Independent ECG Reconstruction

Abstract

Reconstructing a 12-lead electrocardiogram (ECG) from a reduced lead set is an ill-posed inverse problem due to anatomical variability. Standard deep learning methods often ignore underlying cardiac pathology losing vital morphology in precordial leads. We propose Pathology-Aware Multi-View Contrastive Learning, a framework that regularizes the latent space through a pathological manifold. Our architecture integrates high-fidelity time-domain waveforms with pathology-aware embeddings learned via supervised contrastive alignment. By maximizing mutual information between latent representations and clinical labels, the framework learns to filter anatomical "nuisance" variables. On the PTB-XL dataset, our method achieves approx. 76\% reduction in RMSE compared to state-of-the-art model in patient-independent setting. Cross-dataset evaluation on the PTB Diagnostic Database confirms superior generalization, bridging the gap between hardware portability and diagnostic-grade reconstruction.
Paper Structure (15 sections, 4 equations, 4 figures, 4 tables)

This paper contains 15 sections, 4 equations, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Proposed Methodology
  4. Signal Cleaning and Segmentation
  5. Pathology-aware Latent Representation
  6. Normalization and Fusion
  7. Stacked Latent Decoder
  8. Experiments
  9. Data Partitioning and Protocol
  10. Training Configuration and Evaluation Metrics
  11. Latent Space Structure and Clinical Separability
  12. Lead Reconstruction Performance
  13. Comparison with Prior Work
  14. Cross-Dataset Generalization
  15. Conclusion

Figures (4)

  • Figure 1: Proposed ECG reconstruction framework. (a) Preprocessing and segmentation, (b) Multi-View Supervised contrastive pretraining to learn pathology-aware latent representations, and (c) Reconstruction network that integrates contrastive representation with clean ECG signals via a temporal decoder.
  • Figure 2: k-NN affinity matrices ($k=10$) comparing (a) the clean baseline $\mathbf{x}$ and (b) the learned latent representation $\mathbf{h}$.
  • Figure 3: Radar plot showing lower RMSE for C-h model for few most and least abundant diagnostic class. $n$ represents the number of segments in test fold. The closer the vertex to center, the lower is the RMSE. The y-values for each ring correspond to [0.05, 0.075, 0.10, 0.125, 0.15] starting from center.
  • Figure 4: Qualitative heartbeat-level reconstruction examples across different diagnostic classes (NORM, INJAS, RVH) for leads V1,V3--V6. The C-h configuration more closely follows the ground truth compared to the C baseline, particularly in capturing QRS complex amplitude and T-wave morphology.