Overview of Scanner Invariant Representations

TL;DR

This paper reviews an unsupervised method for creating scanner-invariant image representations that mitigate bias from multiple data sources without needing paired images, enhancing data harmonization.

Contribution

It provides an overview of a novel unsupervised approach using invariant representations to correct scanner biases without requiring correspondence data.

Findings

Invariant representations can effectively remove scanner bias.

The method does not require paired or traveling phantom data.

It preserves underlying image structure while removing source information.

Abstract

Pooled imaging data from multiple sources is subject to bias from each source. Studies that do not correct for these scanner/site biases at best lose statistical power, and at worst leave spurious correlations in their data. Estimation of the bias effects is non-trivial due to the paucity of data with correspondence across sites, so called "traveling phantom" data, which is expensive to collect. Nevertheless, numerous solutions leveraging direct correspondence have been proposed. In contrast to this, Moyer et al. (2019) proposes an unsupervised solution using invariant representations, one which does not require correspondence and thus does not require paired images. By leveraging the data processing inequality, an invariant representation can then be used to create an image reconstruction that is uninformative of its original source, yet still faithful to the underlying structure. In the present abstract we provide an overview of this method.