# A Heteroscedastic Uncertainty Model for Decoupling Sources of MRI Image Quality

arXiv: https://arxiv.org/abs/2001.11927 · HTML: https://mlsanity.com/paper/2001.11927/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2020.

## Built on by (most cited first, 7 of 7)

- [Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysis](https://mlsanity.com/paper/2210.03736/) (2022)
- [A review of uncertainty quantification in medical image analysis: probabilistic and non-probabilistic methods](https://mlsanity.com/paper/2310.06873/) (2023)
- [Propagation and Attribution of Uncertainty in Medical Imaging Pipelines](https://mlsanity.com/paper/2309.16831/) (2023)
- [Estimating MRI Image Quality via Image Reconstruction Uncertainty](https://mlsanity.com/paper/2106.10992/) (2021)
- [A Decoupled Uncertainty Model for MRI Segmentation Quality Estimation](https://mlsanity.com/paper/2109.02413/) (2021)
- [An efficient semi-supervised quality control system trained using physics-based MRI-artefact generators and adversarial training](https://mlsanity.com/paper/2206.03359/) (2022)
- [SLYKLatent: A Learning Framework for Gaze Estimation Using Deep Facial Feature Learning](https://mlsanity.com/paper/2402.01555/) (2024)

## Abstract (arXiv)

Quality control (QC) of medical images is essential to ensure that downstream analyses such as segmentation can be performed successfully. Currently, QC is predominantly performed visually at significant time and operator cost. We aim to automate the process by formulating a probabilistic network that estimates uncertainty through a heteroscedastic noise model, hence providing a proxy measure of task-specific image quality that is learnt directly from the data. By augmenting the training data with different types of simulated k-space artefacts, we propose a novel cascading CNN architecture based on a student-teacher framework to decouple sources of uncertainty related to different k-space augmentations in an entirely self-supervised manner. This enables us to predict separate uncertainty quantities for the different types of data degradation. While the uncertainty measures reflect the presence and severity of image artefacts, the network also provides the segmentation predictions given the quality of the data. We show models trained with simulated artefacts provide informative measures of uncertainty on real-world images and we validate our uncertainty predictions on problematic images identified by human-raters.