TY - JOUR
T1 - DeepQSM - using deep learning to solve the dipole inversion for quantitative susceptibility mapping
AU - Bollmann, Steffen
AU - Rasmussen, Kasper Gade Bøtker
AU - Kristensen, Mads
AU - Blendal, Rasmus Guldhammer
AU - Østergaard, Lasse Riis
AU - Plocharski, Maciej
AU - O'Brien, Kieran
AU - Langkammer, Christian
AU - Janke, Andrew
AU - Barth, Markus
N1 - Copyright © 2019 Elsevier Inc. All rights reserved.
PY - 2019/7
Y1 - 2019/7
N2 - Quantitative susceptibility mapping (QSM) is based on magnetic resonance imaging (MRI) phase measurements and has gained broad interest because it yields relevant information on biological tissue properties, predominantly myelin, iron and calcium in vivo. Thereby, QSM can also reveal pathological changes of these key components in widespread diseases such as Parkinson's disease, Multiple Sclerosis, or hepatic iron overload. While the ill-posed field-to-source-inversion problem underlying QSM is conventionally assessed by the means of regularization techniques, we trained a fully convolutional deep neural network - DeepQSM - to directly invert the magnetic dipole kernel convolution. DeepQSM learned the physical forward problem using purely synthetic data and is capable of solving the ill-posed field-to-source inversion on in vivo MRI phase data. The magnetic susceptibility maps reconstructed by DeepQSM enable identification of deep brain substructures and provide information on their respective magnetic tissue properties. In summary, DeepQSM can invert the magnetic dipole kernel convolution and delivers robust solutions to this ill-posed problem.
AB - Quantitative susceptibility mapping (QSM) is based on magnetic resonance imaging (MRI) phase measurements and has gained broad interest because it yields relevant information on biological tissue properties, predominantly myelin, iron and calcium in vivo. Thereby, QSM can also reveal pathological changes of these key components in widespread diseases such as Parkinson's disease, Multiple Sclerosis, or hepatic iron overload. While the ill-posed field-to-source-inversion problem underlying QSM is conventionally assessed by the means of regularization techniques, we trained a fully convolutional deep neural network - DeepQSM - to directly invert the magnetic dipole kernel convolution. DeepQSM learned the physical forward problem using purely synthetic data and is capable of solving the ill-posed field-to-source inversion on in vivo MRI phase data. The magnetic susceptibility maps reconstructed by DeepQSM enable identification of deep brain substructures and provide information on their respective magnetic tissue properties. In summary, DeepQSM can invert the magnetic dipole kernel convolution and delivers robust solutions to this ill-posed problem.
KW - Deep learning
KW - Dipole inversion
KW - Ill-posed problem
KW - Quantitative susceptibility mapping
UR - http://www.scopus.com/inward/record.url?scp=85064151328&partnerID=8YFLogxK
U2 - 10.1016/j.neuroimage.2019.03.060
DO - 10.1016/j.neuroimage.2019.03.060
M3 - Journal article
C2 - 30935908
SN - 1053-8119
VL - 195
SP - 373
EP - 383
JO - NeuroImage
JF - NeuroImage
ER -