# Harmonization and the Worst Scanner Syndrome

arXiv: https://arxiv.org/abs/2101.06255 · HTML: https://mlsanity.com/paper/2101.06255/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 14 references that are in the map.
- First posted on arXiv 15 Jan 2021.

## Builds on (most cited first, 11 of 11)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Unsupervised domain adaptation in brain lesion segmentation with adversarial networks](https://mlsanity.com/paper/1612.08894/) (2016)
- [DIVA: Domain Invariant Variational Autoencoders](https://mlsanity.com/paper/1905.10427/) (2019)
- [Invariant Representations without Adversarial Training](https://mlsanity.com/paper/1805.09458/) (2018)
- [Unsupervised Domain Adaptation via Disentangled Representations: Application to Cross-Modality Liver Segmentation](https://mlsanity.com/paper/1907.13590/) (2019)
- [Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects](https://mlsanity.com/paper/1910.04597/) (2019)
- [A Learning Strategy for Contrast-agnostic MRI Segmentation](https://mlsanity.com/paper/2003.01995/) (2020)
- [Scanner Invariant Representations for Diffusion MRI Harmonization](https://mlsanity.com/paper/1904.05375/) (2019)
- [Scanner Invariant Multiple Sclerosis Lesion Segmentation from MRI](https://mlsanity.com/paper/1910.10035/) (2019)

## Built on by (most cited first, 2 of 2)

- [Synthetic Data for Robust Stroke Segmentation](https://mlsanity.com/paper/2404.01946/) (2024)
- [Adapting Machine Learning Diagnostic Models to New Populations Using a Small Amount of Data: Results from Clinical Neuroscience](https://mlsanity.com/paper/2308.03175/) (2023)

## Abstract (arXiv)

We show that for a wide class of harmonization/domain-invariance schemes several undesirable properties are unavoidable. If a predictive machine is made invariant to a set of domains, the accuracy of the output predictions (as measured by mutual information) is limited by the domain with the least amount of information to begin with. If a real label value is highly informative about the source domain, it cannot be accurately predicted by an invariant predictor. These results are simple and intuitive, but we believe that it is beneficial to state them for medical imaging harmonization.