3 papers
physics.med-ph2026
A novel method for analysis of transient morphological changes in quasiperiodic physiological signals and their neurogenic correlates
Tomasz Gradowski, Damian WalÄ g, Damian Waląg +3
Conventional ECG visualization and analysis methods typically emphasize either waveform morphology or rhythm variability. This work presents a visualization framework for quasiperi…
eess.SP2025
Deep learning model for ECG reconstruction reveals the information content of ECG leads
Tomasz Gradowski, Teodor Buchner
This study introduces a deep learning model based on the U-net architecture to reconstruct missing leads in electrocardiograms (ECGs). The model was trained to reconstruct 12-lead…
physics.med-ph2025
Physically motivated projection of the electrocardiogram -- a feasibility study
Sebastian Wildowicz, Tomasz Gradowski, Paulina Figura +3
We present PhysECG: a physically motivated projection of the 12 lead electrocardiogram, supported by a deep learning model trained on 21,799 recordings from the PTB-XL database and…