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

Choice of training label matters: how to best use deep learning for quantitative MRI parameter estimation

Epstein, Sean; Bray, Timothy; Hall-Craggs, margaret; Zhang, Hui; (2024) Choice of training label matters: how to best use deep learning for quantitative MRI parameter estimation. Journal of Machine Learning for Biomedical Imaging , 2 pp. 586-610. 10.59275/j.melba.2024-geb5. Green open access

[thumbnail of Bray_2024_002.pdf]
Preview
Text
Bray_2024_002.pdf

Download (2MB) | Preview

Abstract

Deep learning (DL) is gaining popularity as a parameter estimation method for quantitative MRI. A range of competing implementations have been proposed, relying on either supervised or self-supervised learning. Self-supervised approaches, sometimes referred to as unsupervised, have been loosely based on auto-encoders, whereas supervised methods have, to date, been trained on groundtruth labels. These two learning paradigms have been shown to have distinct strengths. Notably, self-supervised approaches offer lower-bias parameter estimates than their supervised alternatives. This result is counterintuitive – incorporating prior knowledge with supervised labels should, in theory, lead to improved accuracy. In this work, we show that this apparent limitation of supervised approaches stems from the naïve choice of groundtruth training labels. By training on labels which are deliberately not groundtruth, we show that the low-bias parameter estimation previously associated with self-supervised methods can be replicated – and improved on – within a supervised learning framework. This approach sets the stage for a single, unifying, deep learning parameter estimation framework, based on supervised learning, where trade-offs between bias and variance are made by careful adjustment of training label.

Type: Article
Title: Choice of training label matters: how to best use deep learning for quantitative MRI parameter estimation
Open access status: An open access version is available from UCL Discovery
DOI: 10.59275/j.melba.2024-geb5
Publisher version: https://doi.org/10.59275/j.melba.2024-geb5
Language: English
Additional information: ©2024 Epstein et al.. License: CC-BY 4.0
Keywords: quantitative mri, diffusion mri, deep learning
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 Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences > Div of Medicine
URI: https://discovery.ucl.ac.uk/id/eprint/10186089
Downloads since deposit
5Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item