UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Training data distribution significantly impacts the estimation of tissue microstructure with machine learning

Gyori, N; Palombo, M; Clark, C; Zhang, H; Alexander, D; (2022) Training data distribution significantly impacts the estimation of tissue microstructure with machine learning. Magnetic Resonance in Medicine , 87 (2) pp. 932-947. 10.1002/mrm.29014. Green open access

[thumbnail of Magnetic Resonance in Med - 2021 - Gyori - Training data distribution significantly impacts the estimation of tissue.pdf]
Preview
Text
Magnetic Resonance in Med - 2021 - Gyori - Training data distribution significantly impacts the estimation of tissue.pdf - Published Version

Download (2MB) | Preview

Abstract

Purpose: Supervised machine learning (ML) provides a compelling alternative to traditional model fitting for parameter mapping in quantitative MRI. The aim of this work is to demonstrate and quantify the effect of different training data distributions on the accuracy and precision of parameter estimates when supervised ML is used for fitting. // Methods: We fit a two- and three-compartment biophysical model to diffusion measurements from in-vivo human brain, as well as simulated diffusion data, using both traditional model fitting and supervised ML. For supervised ML, we train several artificial neural networks, as well as random forest regressors, on different distributions of ground truth parameters. We compare the accuracy and precision of parameter estimates obtained from the different estimation approaches using synthetic test data. // Results: When the distribution of parameter combinations in the training set matches those observed in healthy human data sets, we observe high precision, but inaccurate estimates for atypical parameter combinations. In contrast, when training data is sampled uniformly from the entire plausible parameter space, estimates tend to be more accurate for atypical parameter combinations but may have lower precision for typical parameter combinations. // Conclusion: This work highlights that estimation of model parameters using supervised ML depends strongly on the training-set distribution. We show that high precision obtained using ML may mask strong bias, and visual assessment of the parameter maps is not sufficient for evaluating the quality of the estimates.

Type: Article
Title: Training data distribution significantly impacts the estimation of tissue microstructure with machine learning
Open access status: An open access version is available from UCL Discovery
DOI: 10.1002/mrm.29014
Publisher version: https://doi.org/10.1002/mrm.29014
Language: English
Additional information: © 2021 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
Keywords: machine learning; microstructure imaging; model fitting; quantitative MRI training; data distribution
UCL classification: UCL
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences > Div of Biosciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Population Health Sciences > UCL GOS Institute of Child Health
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Population Health Sciences > UCL GOS Institute of Child Health > Developmental Neurosciences Dept
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10141866
Downloads since deposit
14Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item