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

arXiv: https://arxiv.org/abs/2205.05587 · HTML: https://mlsanity.com/paper/2205.05587/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 24 references that are in the map.
- First posted on arXiv 11 May 2022.

## Builds on (most cited first, 5 of 5)

- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Quantitative Susceptibility Mapping using Deep Neural Network: QSMnet](https://mlsanity.com/paper/1803.05627/) (2018)
- [Improved unsupervised physics-informed deep learning for intravoxel incoherent motion modeling and evaluation in pancreatic cancer patients](https://mlsanity.com/paper/2011.01689/) (2020)
- [Model-Informed Machine Learning for Multi-component T2 Relaxometry](https://mlsanity.com/paper/2007.10225/) (2020)
- [Task-driven assessment of experimental designs in diffusion MRI: a computational framework](https://mlsanity.com/paper/2103.08438/) (2021)

## Built on by (most cited first, 8 of 8)

- [Diffusion MRI with Machine Learning](https://mlsanity.com/paper/2402.00019/) (2024)
- [Rician likelihood loss for quantitative MRI using self-supervised deep learning](https://mlsanity.com/paper/2307.07072/) (2023)
- [ssVERDICT: Self-Supervised VERDICT-MRI for Enhanced Prostate Tumour Characterisation](https://mlsanity.com/paper/2309.06268/) (2023)
- [Fitting a Directional Microstructure Model to Diffusion-Relaxation MRI Data with Self-Supervised Machine Learning](https://mlsanity.com/paper/2210.02349/) (2022)
- [MRI Parameter Mapping via Gaussian Mixture VAE: Breaking the Assumption of Independent Pixels](https://mlsanity.com/paper/2411.10772/) (2024)
- [Eddeep: a deep-learning framework for fast eddy-current distortion correction in diffusion MRI](https://mlsanity.com/paper/2607.26292/) (2026)
- [Ultra-Strong Gradient Diffusion MRI with Self-Supervised Learning for Prostate Cancer Characterization](https://mlsanity.com/paper/2512.03196/) (2025)
- [Realistic noise synthesis reduces bias and improves tissue microstructure estimation with supervised machine learning](https://mlsanity.com/paper/2606.02044/) (2026)

## Abstract (arXiv)

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 have offered 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 naive 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.