Probabilistic multi-site MR image harmonization via feature preserving conditional generative adversarial networks

Brain magnetic resonance imaging (MRI) is pivotal in diagnosing and monitoring neurological disorders. However, despite their extensive applications, MR images have certain shortcomings. In particular, factors other than the anatomy of brain tissues influence the intensity distribution of voxels in MR images. These factors include hardware, software, magnetic field strength, and acquisition protocol. This inconsistency poses challenges in multi-site neuroimaging studies, where images are obtained from various devices with minimal control over acquisition parameters. Image harmonization algorithms aim to eliminate non-biological characteristics in MR images through various approaches, including converting images from multiple sites into a format resembling that of a designated target site. Among image harmonization methods, those relying on deep learning algorithms have gained significant attention recently. Nevertheless, certain aspects of deep learning-based image harmonization remain unexplored, notably the integration of probabilistic deep generative models to transform the distribution of MR images to a desired distribution. Inspired by this, we introduced a feature preserving conditional generative adversarial network (FP-cGAN) that converts images from multiple origins into the format of a target site while preserving anatomical features by imposing a novel regularizing constraint. We conduct our experiments on MR images from the SRPBS dataset, which comprises unpaired images in addition to paired (traveling subjects) images from multiple sites. We utilize the unpaired data for training our models and the paired data for evaluation. Furthermore, we compare our results with histogram matching, ImUnity, and CycleGAN, three widely used image harmonization methods. To evaluate robustness and generalizability, we also conduct an extended experiment using heterogeneous public datasets and assess performance using distributional measures. In addition, we analyze the role of the probabilistic formulation by examining the effect of the number of samples and by deriving uncertainty maps from the sample variance. Our experiments demonstrate that the proposed method outperforms the discussed competing approaches while providing meaningful uncertainty estimates.