An Optimized Framework of QSM Mask Generation Using Deep Learning: QSMmask‐Net
NMR in Biomedicine · 2025
DOI: 10.1002/nbm.70057 ↗Kurz gefasst
Fachartikel in der Zeitschrift NMR in Biomedicine, 2025. Verfasst von Gawon Lee und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Hankuk University of Foreign Studies, Yongin, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning, Magnetic Resonance Imaging, Image Processing, Computer-Assisted. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Research Foundation of Korea, Hankuk University of Foreign Studies Research Fund.
Abstract (Originalsprache)
Quantitative susceptibility mapping (QSM) provides the spatial distribution of magnetic susceptibility within tissues through sequential steps: phase unwrapping and echo combination, mask generation, background field removal, and dipole inversion. Accurate mask generation is crucial, as masks excluding regions outside the brain and without holes are necessary to minimize errors and streaking artifacts during QSM reconstruction. Variations in susceptibility values can arise from different mask generation methods, highlighting the importance of optimizing mask creation. In this study, we propose QSMmask‐net, a deep neural network‐based method for generating precise QSM masks. QSMmask‐net achieved the highest Dice score compared to other mask generation methods. Mean susceptibility values using QSMmask‐net masks showed the lowest differences from manual masks (ground truth) in simulations and healthy controls (no significant difference, p > 0.05). Linear regression analysis confirmed a strong correlation with manual masks for hemorrhagic lesions (slope = 0.9814 ± 0.007, intercept = 0.0031 ± 0.001, R 2 = 0.9992, p < 0.05). We have demonstrated that mask generation methods can affect the susceptibility value estimations. QSMmask‐net reduces the labor required for mask generation while providing mask quality comparable to manual methods. The proposed method enables users without specialized expertise to create optimized masks, potentially broadening QSM applicability efficiently.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biomedical Engineering, Hankuk University of Foreign Studies, Yongin, Republic of Korea.
- AIRS Medical, Seoul, Republic of Korea.
- Department of Diagnostic Radiology, Diagnostics Institute, The Cleveland Clinic, Cleveland, Ohio, USA.
ORCID-Profile: Gawon Lee
Förderung
- National Research Foundation of Korea
- Hankuk University of Foreign Studies Research Fund
Zitieren
APA
Lee, G., Jung, W., Sakaie, K. E., & Oh, S. H. (2025). An Optimized Framework of QSM Mask Generation Using Deep Learning: QSMmask‐Net. NMR in Biomedicine. https://doi.org/10.1002/nbm.70057
Vancouver
Lee G, Jung W, Sakaie KE, Oh SH. An Optimized Framework of QSM Mask Generation Using Deep Learning: QSMmask‐Net. NMR in Biomedicine. 2025. doi:10.1002/nbm.70057
BibTeX
@article{Lee2025,
author = {Lee, Gawon and Jung, Woojin and Sakaie, Ken E and Oh, Se-Hong},
title = {An Optimized Framework of QSM Mask Generation Using Deep Learning: QSMmask‐Net},
journal = {NMR in Biomedicine},
year = {2025},
doi = {10.1002/nbm.70057}
}
EUVIMED