Harmonization and the Worst Scanner Syndrome

2021/01/15 by Moyer, Daniel, Golland, Polina · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Quantitative Methods (q-bio.QM) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2101.06255

Abstract

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.

Cited by

• Synthetic Data for Robust Stroke Segmentation

Related

• Overview of Scanner Invariant Representations
• Scanner Invariant Representations for Diffusion MRI Harmonization
• Misdirected Registration Uncertainty
• Accounting for Unobserved Confounding in Domain Generalization
• Invariant Correlation of Representation with Label: Enhancing Domain Generalization in Noisy Environments