Overview of Scanner Invariant Representations

05/29/2020
by   Daniel Moyer, et al.
8

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/10/2019

Scanner Invariant Representations for Diffusion MRI Harmonization

Pooled imaging data from multiple sources is subject to variation betwee...
research
03/26/2018

Removing scanner biases using Generative Adversarial Networks

Magnetic Resonance Imaging (MRI) of the brain has been used to investiga...
research
09/30/2021

Learning Multi-Site Harmonization of Magnetic Resonance Images Without Traveling Human Phantoms

Harmonization improves data consistency and is central to effective inte...
research
08/12/2020

Null-sampling for Interpretable and Fair Representations

We propose to learn invariant representations, in the data domain, to ac...
research
03/02/2022

Weakly Supervised Correspondence Learning

Correspondence learning is a fundamental problem in robotics, which aims...

Please sign up or login with your details

Forgot password? Click here to reset