Scanner invariant representations for diffusion MRI harmonization

• Published in: Magnetic resonance in medicine Vol. 84; no. 4; pp. 2174 - 2189
• Main Authors: Moyer, Daniel, Ver Steeg, Greg, Tax, Chantal M. W., Thompson, Paul M.
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01.10.2020; John Wiley and Sons Inc
• Subjects: Brain - diagnostic imaging; Coders; Computer applications; Data processing; Diffusion; Diffusion Magnetic Resonance Imaging; diffusion MRI; Full Papers—Biophysics and Basic Biomedical Research; harmonization; Image processing; Image Processing, Computer-Assisted; Image reconstruction; Information theory; invariant representation; Invariants; Machine learning; Magnetic resonance imaging; Mapping; Representations; Scanners; Scanning; diffusion MRI; harmonization; invariant representation

Purpose In the present work, we describe the correction of diffusion‐weighted MRI for site and scanner biases using a novel method based on invariant representation. Theory and Methods Pooled imaging data from multiple sources are subject to variation between the sources. Correcting for these biases...