eess.IVApr 29, 2026

Validating the Clinical Utility of CineECG 3D Reconstructions through Cross-Modal Feature Attribution

Authors: Karol DobiczekMaciej MozolewskiSzymon BobekMichał SzafarczykPeter van DamGrzegorz J. Nalepa

Organizations: Department of Human-Centered Artificial Intelligence, Institute of Applied Computer Science, Jagiellonian University, Krakow, Poland · Faculty of Medicine, Jagiellonian University Medical College, Krakow, Poland

Abstract

Deep learning models for 12-lead electrocardiogram (ECG) analysis achieve high diagnostic performance but lack the intuitive interpretability required for clinical integration. Standard feature attribution methods are limited by the inherent difficulty in mapping abstract waveform fluctuations to physical anatomical pathologies. To resolve this, we propose a cross-modal method that projects feature attributions from high-performance 12-lead ECG models onto the CineECG 3D anatomical space. Our study reveals that while models trained directly on CineECG signals suffer from reduced accuracy and incoherent attributions, the proposed mapping mechanism effectively recovers clinically relevant feature rankings. Validated against a ground-truth dataset of 20 cases annotated by domain experts, the mapped explanations yield a Dice score of 0.56, significantly outperforming the 0.47 baseline of standard 12-lead attributions. These findings indicate that cross-modal averaging mapping effectively filters attribution instability and improves the localization of pathological features, combining the diagnostic expressiveness of standard ECG with the intuitive clarity of anatomical visualization.

Explore similar work

CardsList