Generative adversarial networks (GANs) can synthesize high-contrast MRI from lower-contrast input. Targeted translation of parenchymal lesions in multiple sclerosis (MS), as well as visualization of model confidence further augment their utility, provided that the GAN generalizes reliably across different scanners. We here investigate the generalizability of a refined GAN for synthesizing high-contrast double inversion recovery (DIR) images and propose the use of uncertainty maps to further enhance its clinical utility and trustworthiness. A GAN was trained to synthesize DIR from input fluid-attenuated inversion recovery (FLAIR) and T1w of 50 MS patients (training data). In another 50 patients (test data), two blinded readers (R1 and R2) independently quantified lesions in synthetic DIR (synthDIR), acquired DIR (trueDIR) and FLAIR. Of the 50 test patients, 20 were acquired on the same scanner as training data (internal data), while 30 were scanned at different scanners with heterogeneous field strengths and protocols (external data). Lesion-to-Background ratios (LBR) for MS-lesions vs. normal appearing white matter, as well as image quality parameters were calculated. Uncertainty maps were generated to visualize model confidence. Significantly more MS-specific lesions were found in synthDIR compared to FLAIR (R1: 26.7 ± 2.6 vs. 22.5 ± 2.2 p < 0.0001; R2: 22.8 ± 2.2 vs. 19.9 ± 2.0, p = 0.0005). While trueDIR remained superior to synthDIR in R1 [28.6 ± 2.9 vs. 26.7 ± 2.6 (p = 0.0021)], both sequences showed comparable lesion conspicuity in R2 [23.3 ± 2.4 vs. 22.8 ± 2.2 (p = 0.98)]. Importantly, improvements in lesion counts were similar in internal and external data. Measurements of LBR confirmed that lesion-focused GAN training significantly improved lesion conspicuity. The use of uncertainty maps furthermore helped discriminate between MS lesions and artifacts. In conclusion, this multicentric study confirms the external validity of a lesion-focused Deep-Learning tool aimed at MS imaging. When implemented, uncertainty maps are promising to increase the trustworthiness of synthetic MRI.
Usage of MR imaging biomarkers is limited to experts. Automatic quantitative reports provide access for clinicians to data analysis. Automated data analysis was tested for usability in a small cohort of patients with hereditary spastic paraplegia type 4 (SPG4). We analyzed 3T MRI 3D-T1 datasets of n = 25 SPG4 patients and matched healthy controls using a commercial segmentation tool (AIRAscore structure 2.0.1) and standard VBM. In SPG4 total brain volume was reduced by 27.6 percentiles (p = 0.001) caused mainly by white matter loss (− 30.8th, p < 0.001) and stable total gray matter compared to controls. Brain volume loss occurred in: midbrain (− 41.5th, p = 0.001), pons (− 36.5th, p = 0.02), hippocampus (− 20.9th, p = 0.002), and gray matter of the cingulate gyrus (− 17.0th, p = 0.02). Ventricular volumes increased as indirect measures of atrophy. Group comparisons using percentiles aligned with results from VBM analyses. Quantitative imaging reports proved to work as an easily accessible, fully automatic screening tool for clinicians, even in a small cohort of a rare genetic disorder. We could delineate the involvement of white matter and specify involved brain regions. Group comparisons using percentiles provide comparable results to VBM analysis and are, therefore, a suitable and simple screening tool for all clinicians with and without in-depth knowledge of image processing.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.