DeepQSM - using deep learning to solve the dipole inversion for quantitative susceptibility mapping

Steffen Bollmann, Kasper Gade Bøtker Rasmussen, Mads Kristensen, Rasmus Guldhammer Blendal, Lasse Riis Østergaard, Maciej Plocharski, Kieran O'Brien, Christian Langkammer, Andrew Janke, Markus Barth

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

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.

Original languageEnglish
JournalNeuroImage
ISSN1053-8119
DOIs
Publication statusE-pub ahead of print - 29 Mar 2019

Fingerprint

Magnetic Resonance Imaging
Learning
Iron Overload
Myelin Sheath
Multiple Sclerosis
Parkinson Disease
Iron
Calcium
Liver
Brain

Cite this

Bollmann, Steffen ; Rasmussen, Kasper Gade Bøtker ; Kristensen, Mads ; Blendal, Rasmus Guldhammer ; Østergaard, Lasse Riis ; Plocharski, Maciej ; O'Brien, Kieran ; Langkammer, Christian ; Janke, Andrew ; Barth, Markus. / DeepQSM - using deep learning to solve the dipole inversion for quantitative susceptibility mapping. In: NeuroImage. 2019.
@article{1824c44c4f964022a6b2a91549f9676f,
title = "DeepQSM - using deep learning to solve the dipole inversion for quantitative susceptibility mapping",
abstract = "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.",
author = "Steffen Bollmann and Rasmussen, {Kasper Gade B{\o}tker} and Mads Kristensen and Blendal, {Rasmus Guldhammer} and {\O}stergaard, {Lasse Riis} and Maciej Plocharski and Kieran O'Brien and Christian Langkammer and Andrew Janke and Markus Barth",
note = "Copyright {\circledC} 2019. Published by Elsevier Inc.",
year = "2019",
month = "3",
day = "29",
doi = "10.1016/j.neuroimage.2019.03.060",
language = "English",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Elsevier",

}

DeepQSM - using deep learning to solve the dipole inversion for quantitative susceptibility mapping. / Bollmann, Steffen; Rasmussen, Kasper Gade Bøtker; Kristensen, Mads; Blendal, Rasmus Guldhammer; Østergaard, Lasse Riis; Plocharski, Maciej; O'Brien, Kieran; Langkammer, Christian; Janke, Andrew; Barth, Markus.

In: NeuroImage, 29.03.2019.

Research output: Contribution to journalJournal articleResearchpeer-review

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. Published by Elsevier Inc.

PY - 2019/3/29

Y1 - 2019/3/29

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.

U2 - 10.1016/j.neuroimage.2019.03.060

DO - 10.1016/j.neuroimage.2019.03.060

M3 - Journal article

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -