Contrast-Free Myocardial Infarction Segmentation with Attention U-Net
Diagnostics · 04.03.2026 · 16 (5) · 768
DOI: 10.3390/diagnostics16050768 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 04.03.2026. Verfasst von Khaled Ali Deeb und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Processing and Management Systems, Bauman Moscow State Technical University, 105005 Moscow, Russia. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Cardiovascular magnetic resonance (CMR) is the clinical gold standard for assessing cardiac anatomy and function. However, the manual segmentation of cardiac structures and myocardial infarction (MI) is time-consuming, prone to inter-observer variability, and often depends on contrast-enhanced imaging. Although deep learning (DL) has enabled substantial automation, challenges remain in generalizability, particularly for MI detection from non-contrast cine CMR.
Objective
This study proposes a comprehensive DL-based framework for automatic segmentation of cardiac structures and myocardial infarction using contrast-free cine CMR.
Methods
The framework integrates multiple convolutional neural network (CNN) architectures for cardiac structure segmentation with an attention-based deep learning model for MI localization. Post-processing refinement using stacked autoencoders and active contour modeling is applied to improve anatomical consistency. Segmentation performance is evaluated using overlap-based and boundary-based metrics, including the Dice Similarity Coefficient (DSC), Mean Contour Distance (MCD), and Hausdorff Distance (HD).
Results
The best-performing model achieved Dice scores of 0.93 ± 0.05 for the left ventricular (LV) cavity, 0.89 ± 0.04 for the LV myocardium, and 0.91 ± 0.06 for the right ventricular (RV) cavity, with consistently low boundary errors across all structures. Myocardial infarction segmentation achieved a Dice score of 0.80 ± 0.02 with high recall, demonstrating reliable infarct localization without the use of contrast agents.
Conclusions
By enabling accurate cardiac structure and myocardial infarction segmentation from contrast-free cine CMR, the proposed framework supports broader clinical applicability, particularly for patients with contraindications to gadolinium-based contrast agents and in emergency or resource-limited settings. This approach facilitates scalable, contrast-independent cardiac assessment.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Information Processing and Management Systems, Bauman Moscow State Technical University, 105005 Moscow, Russia.
- Department of Medical and Technical Information Technology, Bauman Moscow State Technical University, 105005 Moscow, Russia.
- Department of Biomedical Technologies, Bauman Moscow State Technical University, 105005 Moscow, Russia.
ORCID-Profile: Alexey Tikhomirov, Ahmad Hammoud
Zitieren
APA
Ali Deeb, K., Alshelle, Y., Hammoud, H., Briko, A., Kapravchuk, V., Tikhomirov, A., Latypova, A., & Hammoud, A. (2026). Contrast-Free Myocardial Infarction Segmentation with Attention U-Net. Diagnostics, 16(5), 768. https://doi.org/10.3390/diagnostics16050768
Vancouver
Ali Deeb K, Alshelle Y, Hammoud H, Briko A, Kapravchuk V, Tikhomirov A, et al. Contrast-Free Myocardial Infarction Segmentation with Attention U-Net. Diagnostics. 2026;16(5):768. doi:10.3390/diagnostics16050768
BibTeX
@article{AliDeeb2026,
author = {Ali Deeb, Khaled and Alshelle, Yasmeen and Hammoud, Hala and Briko, Andrey and Kapravchuk, Vladislava and Tikhomirov, Alexey and Latypova, Amaliya and Hammoud, Ahmad},
title = {Contrast-Free Myocardial Infarction Segmentation with Attention U-Net},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {5},
pages = {768},
doi = {10.3390/diagnostics16050768}
}
EUVIMED