Similarity Metrics for MR Image-To-Image Translation

Image-to-image translation can create large impact in medical imaging, for instance the possibility to synthetically transform images to other modalities, sequence types, higher resolutions or lower noise levels. In order to assure a high level of patient safety, these methods are mostly validated by human reader studies, which require a considerable amount of time and costs. Quantitative metrics have been used to complement such studies and to provide reproducible and objective assessment of synthetic images. Even though the SSIM and PSNR metrics are extensively used, they do not detect all types of errors in synthetic images as desired. Other metrics could provide additional useful evaluation. In this study, we give an overview and a quantitative analysis of 15 metrics for assessing the quality of synthetically generated images. We include 11 full-reference metrics (SSIM, MS-SSIM, CW-SSIM, PSNR, MSE, NMSE, MAE, LPIPS, DISTS, NMI and PCC), three non-reference metrics (BLUR, MLC, MSLC) and one downstream task segmentation metric (DICE) to detect 11 kinds of typical distortions and artifacts that occur in MR images. In addition, we analyze the influence of four prominent normalization methods (Minmax, cMinmax, Zscore and Quantile) on the different metrics and distortions. Finally, we provide adverse examples to highlight pitfalls in metric assessment and derive recommendations for effective usage of the analyzed similarity metrics for evaluation of image-to-image translation models.