Model‐based self‐supervised learning for quantitative assessment of myocardial oxygen extraction fraction and myocardial blood volume
Magnetic Resonance in Medicine · 2025
DOI: 10.1002/mrm.30555 ↗Kurz gefasst
Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2025. Verfasst von Qi Huang und 12 weiteren Autor:innen. Beteiligte Einrichtung: Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, Missouri, USA. Hauptthemen laut MEDLINE: Oxygen, Myocardial Infarction, Supervised Machine Learning, Myocardium. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NHLBI NIH HHS, NCATS NIH HHS, NIH CTSA.
Abstract (Originalsprache)
Purpose
To develop a model‐driven, self‐supervised deep learning network for end‐to‐end simultaneous mapping of myocardial oxygen extraction fraction (mOEF) and myocardial blood volume (MBV).
Methods
An asymmetrical spin echo–prepared sequence was used to acquire mOEF and MBV images. By integrating a physical model into the training process, a self‐supervised learning (SSL) pattern can be regulated. A loss function consisted of the mean squared error, plus cosine similarity was used to improve the performance of network predictions for estimating mOEF and MBV simultaneously. The SSL network was trained and evaluated using simulated data with ground truths and human data in vivo from 10 healthy subjects and 10 patients with myocardial infarction.
Results
In the simulation study, the SSL method demonstrated the ability of generating relatively accurate mOEF, MBV, and ΔB maps simultaneously. In the in vivo study, healthy volunteers had an average mOEF of 0.6–0.7 and MBV of 0.11–0.13, comparable to literature‐reported values. In the myocardial infarction regions, the average mOEF and MBV in 5 tested patients reduced to 0.45 ± 0.09 and 0.09 ± 0.02, which were significantly lower ( p < 0.001) than those in normal regions (0.67 ± 0.04 and 0.13 ± 0.01, respectively).
Conclusion
This work has demonstrated the initial feasibility of generating mOEF and MBV maps simultaneously by a model‐driven, self‐supervised learning method.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, Missouri, USA.
- Department of Computer Science, University of Texas Rio Grande Valley, Edinburg, Texas, USA.
- Department of Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China.
- Department of Radiology & Biomedical Imaging, University of California, San Francisco, California, USA.
ORCID-Profile: Qi Huang, Cihat Eldeniz, Jingliang Cheng
Förderung
- NHLBI NIH HHS
- NCATS NIH HHS
- NIH CTSA
- American Heart Association
- Georgia Clinical and Translational Science Alliance
Zitieren
APA
Huang, Q., Tang, H., Wang, K., Li, R., Eldeniz, C., Nguyen, N., Schindler, T. H., Peterson, L. R., Yang, Y., Yan, Y., Cheng, J., Woodard, P. K., & Zheng, J. (2025). Model‐based self‐supervised learning for quantitative assessment of myocardial oxygen extraction fraction and myocardial blood volume. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.30555
Vancouver
Huang Q, Tang H, Wang K, Li R, Eldeniz C, Nguyen N, et al. Model‐based self‐supervised learning for quantitative assessment of myocardial oxygen extraction fraction and myocardial blood volume. Magnetic Resonance in Medicine. 2025. doi:10.1002/mrm.30555
BibTeX
@article{Huang2025,
author = {Huang, Qi and Tang, Haoteng and Wang, Keyan and Li, Ran and Eldeniz, Cihat and Nguyen, Natalie and Schindler, Thomas H and Peterson, Linda R and Yang, Yang and Yan, Yan and Cheng, Jingliang and Woodard, Pamela K and Zheng, Jie},
title = {Model‐based self‐supervised learning for quantitative assessment of myocardial oxygen extraction fraction and myocardial blood volume},
journal = {Magnetic Resonance in Medicine},
year = {2025},
doi = {10.1002/mrm.30555}
}
EUVIMED