χ‐sepnet: Deep Neural Network for Magnetic Susceptibility Source Separation

• Published in: Human brain mapping Vol. 46; no. 2; pp. e70136 - n/a
• Main Authors: Kim, Minjun, Ji, Sooyeon, Kim, Jiye, Min, Kyeongseon, Jeong, Hwihun, Youn, Jonghyo, Kim, Taechang, Jang, Jinhee, Bilgic, Berkin, Shin, Hyeong‐Geol, Lee, Jongho
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.02.2025
• Subjects: Adult; Algorithms; Artificial neural networks; Autoimmune diseases; Bandwidths; Brain; Brain - diagnostic imaging; Brain mapping; Data acquisition; Deep Learning; Diamagnetism; Dipoles; Estimation; Evaluation; Female; Frequency shift; Humans; Image Processing, Computer-Assisted - methods; Lesions; Localization; Machine learning; Magnetic permeability; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Magnetic susceptibility; Magnetoencephalography - methods; Male; Mapping; Multiple sclerosis; Neural networks; Neural Networks, Computer; Orientation behavior; Pipelines; Qualitative analysis; Quantitative analysis; Regularization; Separation; Susceptibility
• ISSN: 1065-9471; 1097-0193; 1097-0193
• DOI: 10.1002/hbm.70136

ABSTRACT Magnetic susceptibility source separation (χ‐separation), an advanced quantitative susceptibility mapping (QSM) method, enables the separate estimation of paramagnetic and diamagnetic susceptibility source distributions in the brain. Similar to QSM, it requires solving the ill‐conditioned p...