SHARQnet - Sophisticated harmonic artifact reduction in quantitative susceptibility mapping using a deep convolutional neural network
| Autor: | Kieran O'Brien, Amir Fazlollahi, Lasse Riis Østergaard, Mathias Vassard Olsen, Morten Skaarup Larsen, Mads Jozwiak Pedersen, Christian Langkammer, Matilde Holm Kristensen, Markus Barth, Steffen Bollmann |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Background field correction
Biophysics Convolutional neural network Artifact reduction 030218 nuclear medicine & medical imaging 03 medical and health sciences Deep Learning 0302 clinical medicine Image Processing Computer-Assisted Humans Radiology Nuclear Medicine and imaging Hepatic iron Radiological and Ultrasound Technology business.industry Deep learning Feed forward Brain Quantitative susceptibility mapping Magnetic Resonance Imaging Kernel (image processing) Artificial intelligence Artifacts business Algorithm 030217 neurology & neurosurgery |
| Zdroj: | Bollmann, S, Kristensen, M H, Larsen, M S, Olsen, M V, Pedersen, M J, Østergaard, L R, O'Brien, K, Langkammer, C, Fazlollahi, A & Barth, M 2019, ' SHARQnet-Sophisticated harmonic artifact reduction in quantitative susceptibility mapping using a deep convolutional neural network ', Medical Physics, vol. 29, no. 2, pp. 139-149 . https://doi.org/10.1016/j.zemedi.2019.01.001 |
| DOI: | 10.1016/j.zemedi.2019.01.001 |
| Popis: | Quantitative susceptibility mapping (QSM) reveals pathological changes in widespread diseases such as Parkinson’s disease, Multiple Sclerosis, or hepatic iron overload. QSM requires multiple processing steps after the acquisition of magnetic resonance imaging (MRI) phase measurements such as unwrapping, background field removal and the solution of an ill-posed field-to-source-inversion. Current techniques utilize iterative optimization procedures to solve the inversion and background field correction, which are computationally expensive and lead to suboptimal or over-regularized solutions requiring a careful choice of parameters that make a clinical application of QSM challenging. We have previously demonstrated that a deep convolutional neural network can invert the magnetic dipole kernel with a very efficient feed forward multiplication not requiring iterative optimization or the choice of regularization parameters. In this work, we extended this approach to remove background fields in QSM. The prototype method, called SHARQnet, was trained on simulated background fields and tested on 3T and 7T brain datasets. We show that SHARQnet outperforms current background field removal procedures and generalizes to a wide range of input data without requiring any parameter adjustments. In summary, we demonstrate that the solution of ill-posed problems in QSM can be achieved by learning the underlying physics causing the artifacts and removing them in an efficient and reliable manner and thereby will help to bring QSM towards clinical applications. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|