Feather-Light Fourier Domain Adaptation in Magnetic Resonance Imaging

TL;DR

This paper introduces a lightweight, test-time domain adaptation method for MRI that replaces low-frequency Fourier components to improve model generalization across different hardware and clinical settings, matching complex models' performance.

Contribution

It presents a simple, training-free Fourier-based domain adaptation technique that effectively enhances MRI model generalization across diverse data sources.

Findings

Achieves state-of-the-art performance with minimal complexity

Effective across various degrees of domain shift

Outperforms more complex deep adaptation models

Abstract

Generalizability of deep learning models may be severely affected by the difference in the distributions of the train (source domain) and the test (target domain) sets, e.g., when the sets are produced by different hardware. As a consequence of this domain shift, a certain model might perform well on data from one clinic, and then fail when deployed in another. We propose a very light and transparent approach to perform test-time domain adaptation. The idea is to substitute the target low-frequency Fourier space components that are deemed to reflect the style of an image. To maximize the performance, we implement the "optimal style donor" selection technique, and use a number of source data points for altering a single target scan appearance (Multi-Source Transferring). We study the effect of severity of domain shift on the performance of the method, and show that our training-free approach reaches the state-of-the-art level of complicated deep domain adaptation models. The code for our experiments is released.