Instant tissue field and magnetic susceptibility mapping from MRI raw phase using Laplacian enhanced deep neural networks
Yang Gao,
Zhuang Xiong,
Amir Fazlollahi,
Peter J Nestor,
Viktor Vegh,
Fatima Nasrallah,
Craig Winter,
G. Bruce Pike,
Stuart Crozier,
Feng Liu,
Hongfu Sun
Affiliations
Yang Gao
School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
Zhuang Xiong
School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
Amir Fazlollahi
Queensland Brain Institute, University of Queensland, Brisbane, Australia
Peter J Nestor
Queensland Brain Institute, University of Queensland, Brisbane, Australia
Viktor Vegh
Centre for Advanced Imaging, University of Queensland, Brisbane, Australia; ARC Training Centre for Innovation in Biomedical Imaging Technology, Brisbane, Australia
Fatima Nasrallah
Queensland Brain Institute, University of Queensland, Brisbane, Australia
Craig Winter
Kenneth G Jamieson Department of Neurosurgery, Royal Brisbane and Women's Hospital, Brisbane, Australia; Centre for Clinical Research, University of Queensland, Brisbane, Australia; School of Mechanical, Medical and Process Engineering, Queensland University of Technology, Brisbane, Australia
G. Bruce Pike
Departments of Radiology and Clinical Neurosciences, Hotchkiss Brain Institute, University of Calgary, Calgary, Canada
Stuart Crozier
School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
Feng Liu
School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
Hongfu Sun
School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia; Corresponding author at: Room 540, General Purpose South (Building 78), University of Queensland, St Lucia, QLD, 4072, Australia.
Quantitative susceptibility mapping (QSM) is an MRI post-processing technique that produces spatially resolved magnetic susceptibility maps from phase data. However, the traditional QSM reconstruction pipeline involves multiple non-trivial steps, including phase unwrapping, background field removal, and dipole inversion. These intermediate steps not only increase the reconstruction time but accumulates errors. This study aims to overcome existing limitations by developing a Laplacian-of-Trigonometric-functions (LoT) enhanced deep neural network for near-instant quantitative field and susceptibility mapping (i.e., iQFM and iQSM) from raw MRI phase data. The proposed iQFM and iQSM methods were compared with established reconstruction pipelines on simulated and in vivo datasets. In addition, experiments on patients with intracranial hemorrhage and multiple sclerosis were also performed to test the generalization of the proposed neural networks. The proposed iQFM and iQSM methods in healthy subjects yielded comparable results to those involving the intermediate steps while dramatically improving reconstruction accuracies on intracranial hemorrhages with large susceptibilities. High susceptibility contrast between multiple sclerosis lesions and healthy tissue was also achieved using the proposed methods. Comparative studies indicated that the most significant contributor to iQFM and iQSM over conventional multi-step methods was the elimination of traditional Laplacian unwrapping. The reconstruction time on the order of minutes for traditional approaches was shortened to around 0.1 s using the trained iQFM and iQSM neural networks.
