χ ‐sepnet: Deep Neural Network for Magnetic Susceptibility Source Separation
Human Brain Mapping · 2025-02 · 46 (2)
DOI: 10.1002/hbm.70136 ↗Kurz gefasst
Fachartikel in der Zeitschrift Human Brain Mapping, online erschienen am 21.01.2025. Verfasst von Minjun Kim und 10 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory for Imaging Science and Technology, Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning, Magnetic Resonance Imaging, Neural Networks, Computer, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Research Foundation of Korea, Institute of New Media and Communications, Seoul National University, Institute of Engineering Research, Seoul National University.
Abstract (Originalsprache)
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 problem of dipole inversion, suffering from so‐called streaking artifacts. Additionally, the method utilizes reversible transverse relaxation () to complement frequency shift information for estimating susceptibility source concentrations, requiring time‐consuming data acquisition for (e.g., multi‐echo spin‐echo) in addition to multi‐echo GRE data for . To address these challenges, we develop a new deep learning network, χ ‐sepnet, and propose two deep learning‐based susceptibility source separation pipelines, χ ‐sepnet‐ for inputs with multi‐echo GRE and multi‐echo spin‐echo (or turbo spin‐echo) and χ‐ sepnet‐ for input with multi‐echo GRE only. The neural network is trained using multiple head orientation data that provide streaking artifact‐free labels, generating high‐quality χ ‐separation maps. The evaluation of the pipelines encompasses both qualitative and quantitative assessments in healthy subjects, and visual inspection of lesion characteristics in multiple sclerosis patients. The susceptibility source‐separated maps of the proposed pipelines delineate detailed brain structures with substantially reduced artifacts compared to those from the conventional regularization‐based reconstruction methods. In quantitative analysis, χ ‐sepnet‐ achieves the best outcomes followed by χ‐ sepnet‐, outperforming the conventional methods. When the lesions of multiple sclerosis patients are classified into subtypes, most lesions are identified as the same subtype in the maps from χ‐ sepnet‐ and χ‐ sepnet‐ (paramagnetic susceptibility: 99.6% and diamagnetic susceptibility: 98.4%; both out of 250 lesions). The χ‐ sepnet‐ pipeline, which only requires multi‐echo GRE data, has demonstrated its potential to offer broad clinical and scientific applications, although further evaluations for various diseases and pathological conditions are necessary.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Laboratory for Imaging Science and Technology, Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea.
- Division of Computer Engineering, Hankuk University of Foreign Studies, Yongin, Republic of Korea.
- Department of Radiology, Seoul St Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea.
- Institute for Precision Health, University of California, Irvine, California, USA.
- Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USA.
- F.M. Kirby Research Center for Functional Brain Imaging, Kennedy Krieger Institute, Baltimore, Maryland, USA.
ORCID-Profile: Minjun Kim, Sooyeon Ji, Jiye Kim, Kyeongseon Min, Hwihun Jeong, Jonghyo Youn, Taechang Kim, Jinhee Jang, Berkin Bilgic, Hyeong-Geol Shin, Jongho Lee
Förderung
- National Research Foundation of Korea
- Institute of New Media and Communications, Seoul National University
- Institute of Engineering Research, Seoul National University
- AI-Bio Research, Seoul National University
- Institute of Information & communications Technology Planning & Evaluation
Zitieren
APA
Kim, M., Ji, S., Kim, J., Min, K., Jeong, H., Youn, J., Kim, T., Jang, J., Bilgic, B., Shin, H. G., & Lee, J. (2025). χ ‐sepnet: Deep Neural Network for Magnetic Susceptibility Source Separation. Human Brain Mapping, 46(2). https://doi.org/10.1002/hbm.70136
Vancouver
Kim M, Ji S, Kim J, Min K, Jeong H, Youn J, et al. χ ‐sepnet: Deep Neural Network for Magnetic Susceptibility Source Separation. Human Brain Mapping. 2025;46(2). doi:10.1002/hbm.70136
BibTeX
@article{Kim2025,
author = {Kim, Minjun and Ji, Sooyeon and Kim, Jiye and Min, Kyeongseon and Jeong, Hwihun and Youn, Jonghyo and Kim, Taechang and Jang, Jinhee and Bilgic, Berkin and Shin, Hyeong-Geol and Lee, Jongho},
title = {χ ‐sepnet: Deep Neural Network for Magnetic Susceptibility Source Separation},
journal = {Human Brain Mapping},
year = {2025},
volume = {46},
number = {2},
doi = {10.1002/hbm.70136}
}
EUVIMED