Harmonizing Flows: Unsupervised MR harmonization based on normalizing flows
This addresses the challenge of inconsistent MRI data from multiple sites for medical imaging applications, though it appears incremental as it builds on existing harmonization techniques.
The paper tackles the problem of harmonizing MR images across different sites without supervision, using normalizing flows to align distributions, and shows superior performance in cross-domain brain MRI segmentation compared to existing methods.
In this paper, we propose an unsupervised framework based on normalizing flows that harmonizes MR images to mimic the distribution of the source domain. The proposed framework consists of three steps. First, a shallow harmonizer network is trained to recover images of the source domain from their augmented versions. A normalizing flow network is then trained to learn the distribution of the source domain. Finally, at test time, a harmonizer network is modified so that the output images match the source domain's distribution learned by the normalizing flow model. Our unsupervised, source-free and task-independent approach is evaluated on cross-domain brain MRI segmentation using data from four different sites. Results demonstrate its superior performance compared to existing methods.