Search papers, labs, and topics across Lattice.
This paper introduces Pathology-Aware Multi-View Contrastive Learning, a novel framework for reconstructing 12-lead ECGs from reduced lead sets while preserving vital morphology often lost by standard deep learning methods. The method regularizes the latent space using a pathological manifold and integrates time-domain waveforms with pathology-aware embeddings learned via supervised contrastive alignment. Experiments on the PTB-XL dataset demonstrate a 76% reduction in RMSE compared to state-of-the-art methods in a patient-independent setting, with superior generalization confirmed through cross-dataset evaluation on the PTB Diagnostic Database.
By explicitly modeling cardiac pathology, this ECG reconstruction method achieves a 76% reduction in error compared to existing techniques, promising more accurate diagnoses from portable devices.
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.
