Journal
MEDICAL IMAGE ANALYSIS
Volume 71, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.media.2021.102045
Keywords
MRI; Microstructure imaging; Diffusion-relaxation MRI; Inverse Laplace transform; Unsupervised learning; Quantitative MRI; Placenta MRI
Categories
Funding
- NIH Human Placenta Project [1U01HD087202-01]
- Wellcome Trust [201374/Z/16/Z]
- EPSRC [N018702, M020533, EP/N018702/1]
- NIHR [RP-2014-05-019]
- National Institute for Health Research (NIHR) Biomedical Research Centre at University College London Hospitals NHS Foundation Trust
- Wellcome EPSRC Centre for Medical Engineering at Kings College London [WT 203148/Z/16/Z]
- University College London
- NIHR Biomedical Research Centre based at Guys and St Thomas NHS Foundation Trust
- Kings College London
- European Union's Horizon 2020 research and innovation programme [666992]
Ask authors/readers for more resources
The algorithm presented in the study offers an unsupervised machine learning technique for spectroscopic analysis of quantitative MRI experiments, showing improved performance over current voxelwise spectral approaches. By simultaneously estimating spectral components and their weightings, the algorithm regularizes ill-posed problems and enables quantitative MRI spectroscopy in a wide range of new applications.
We introduce and demonstrate an unsupervised machine learning technique for spectroscopic analysis of quantitative MRI experiments. Our algorithm supports estimation of one-dimensional spectra from singlecontrast data, and multidimensional correlation spectra from simultaneous multi-contrast data. These spectrum-based approaches allow model-free investigation of tissue properties, but require regularised inversion of a Laplace transform or Fredholm integral, which is an ill-posed calculation. Here we present a method that addresses this limitation in a data-driven way. The algorithm simultaneously estimates a canonical basis of spectral components and voxelwise maps of their weightings, thereby pooling information across whole images to regularise the ill-posed problem. We show in simulations that our algorithm substantially outperforms current voxelwise spectral approaches. We demonstrate the method on multicontrast diffusion-relaxometry placental MRI scans, revealing anatomically-relevant sub-structures, and identifying dysfunctional placentas. Our algorithm vastly reduces the data required to reliably estimate spectra, opening up the possibility of quantitative MRI spectroscopy in a wide range of new applications. Our InSpect code is available at github.com/paddyslator/inspect. (c) 2021 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license ( http://creativecommons.org/licenses/by/4.0/ )
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available