CardioFusion-XAI: a robust multi-scale and explainable framework for cardiac MRI-based disease classification
Cardiology in the Young · 2026-09 · 36 (9) · 1795-1802
DOI: 10.1017/s1047951126123671 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cardiology in the Young, online erschienen am 03.09.2026. Verfasst von Shwetambari Borade und 3 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben.
Abstract (Originalsprache)
Background
Cardiovascular diseases remain a major global health burden, and early diagnosis using cardiac magnetic resonance imaging (MRI) is essential. However, manual interpretation is subjective, while existing deep learning models often show inconsistent preprocessing, limited multi-scale feature learning, and poor interpretability.
Methods
CardioFusion-XAI, a hybrid explainable deep learning framework, was developed for four-class cardiac MRI classification. WaveCLAHE-Net integrates wavelet-based enhancement and contrast-limited adaptive histogram equalisation to improve image quality. CardioXtract Fusion Net combines ResNet-50, EfficientNet-B0, and a Vision Transformer to learn complementary local, multi-scale, and global features. An enhanced classification head performs prediction, while Grad-CAM and t-distributed stochastic neighbour embedding support model interpretability.
Results
Using the Sunnybrook Cardiac Dataset, CardioFusion-XAI achieved 98.89% accuracy, 98.93% precision, a 98.90% F1-score, and an area under the curve of 0.9998.
Conclusions
CardioFusion-XAI provides accurate and interpretable cardiac MRI classification. Further multicentre validation is required before clinical implementation.
Zitieren
APA
Borade, S., Mishra, S., Vairagade, R., & Pawar, P. (2026). CardioFusion-XAI: a robust multi-scale and explainable framework for cardiac MRI-based disease classification. Cardiology in the Young, 36(9), 1795-1802. https://doi.org/10.1017/s1047951126123671
Vancouver
Borade S, Mishra S, Vairagade R, Pawar P. CardioFusion-XAI: a robust multi-scale and explainable framework for cardiac MRI-based disease classification. Cardiology in the Young. 2026;36(9):1795-1802. doi:10.1017/s1047951126123671
BibTeX
@article{Borade2026,
author = {Borade, Shwetambari and Mishra, Saraswati and Vairagade, Rupali and Pawar, Pranali},
title = {CardioFusion-XAI: a robust multi-scale and explainable framework for cardiac MRI-based disease classification},
journal = {Cardiology in the Young},
year = {2026},
volume = {36},
number = {9},
pages = {1795--1802},
doi = {10.1017/s1047951126123671}
}
EUVIMED