To represent the biological variability of clinical neuroimaging populations, it is vital to be able to combine data across scanners and studies. However, different MRI scanners produce images with different characteristics, resulting in a domain shift known as the `harmonisation problem'. Additionally, neuroimaging data is inherently personal in nature, leading to data privacy concerns when sharing the data. To overcome these barriers, we propose an Unsupervised Source-Free Domain Adaptation (SFDA) method, SFHarmony. Through modelling the imaging features as a Gaussian Mixture Model and minimising an adapted Bhattacharyya distance between the source and target features, we can create a model that performs well for the target data whilst having a shared feature representation across the data domains, without needing access to the source data for adaptation or target labels. We demonstrate the performance of our method on simulated and real domain shifts, showing that the approach is applicable to classification, segmentation and regression tasks, requiring no changes to the algorithm. Our method outperforms existing SFDA approaches across a range of realistic data scenarios, demonstrating the potential utility of our approach for MRI harmonisation and general SFDA problems. Our code is available at \url{https://github.com/nkdinsdale/SFHarmony}.

翻译：为了表征临床神经影像群体的生物学变异性，整合来自不同扫描仪和研究的数据至关重要。然而，不同MRI扫描仪生成的图像具有不同特征，导致被称为“一致性问题的域偏移”。此外，神经影像数据本质上具有个人属性，因此在共享数据时引发数据隐私问题。为克服这些障碍，我们提出了一种无监督无源域自适应（SFDA）方法——SFHarmony。通过将影像特征建模为高斯混合模型，并最小化源域与目标域特征之间的自适应巴塔查里亚距离，我们能够创建一个在目标数据上表现优异、同时在各数据域间共享特征表示的模型，且无需访问源数据进行自适应或依赖目标标签。我们在模拟和真实域偏移场景中验证了该方法性能，表明该方法可适用于分类、分割及回归任务，且无需修改算法。在多种现实数据场景下，我们的方法优于现有SFDA方法，证明了该方案在MRI数据一致性问题及通用SFDA问题中的潜在应用价值。我们的代码已发布于 \url{https://github.com/nkdinsdale/SFHarmony}。