Publisher: Wiley Country of Publication: England NLM ID: 8915233 Publication Model: Print Cited Medium: Internet ISSN: 1099-1492 (Electronic) Linking ISSN: 09523480 NLM ISO Abbreviation: NMR Biomed Subsets: MEDLINE

Deep Learning* , Magnetic Resonance Imaging*/methods , Image Processing, Computer-Assisted*/methods, Humans ; Brain/diagnostic imaging ; Male ; Female ; Adult ; Neural Networks, Computer ; Algorithms

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.
(© 2025 The Author(s). NMR in Biomedicine published by John Wiley & Sons Ltd.)