Robustness and Diagnostic Performance of Super-Resolution Fetal Brain MRI

Abstract: Fetal brain MRI relies on rapid multi-view 2D slice acquisitions to reduce motion artifacts caused by fetal movement. However, these stacks are typically low resolution, may suffer from motion corruption, and do not adequately capture 3D anatomy. Super-resolution reconstruction (SRR) methods aim to address these limitations by combining slice-to-volume registration and super-resolution techniques to generate high-resolution (HR) 3D volumes. While several SRR methods have been proposed, their comparative performance - particularly in pathological cases - and their influence on downstream volumetric analysis and diagnostic tasks remain underexplored. In this study, we applied three state-of-the-art SRR method - NiftyMIC, SVRTK, and NeSVoR - to 140 fetal brain MRI scans, including both healthy controls (HC) and pathological cases (PC) with ventriculomegaly (VM). Each HR reconstruction was segmented using the BoUNTi algorithm to extract volumes of nine principal brain structures. We evaluated visual quality, SRR success rates, volumetric measurement agreement, and diagnostic classification performance. NeSVoR demonstrated the highest and most consistent reconstruction success rate (>90%) across both HC and PC groups. Although significant differences in volumetric estimates were observed between SRR methods, classification performance for VM was not affected by the choice of SRR method. These findings highlight NeSVoR's robustness and the resilience of diagnostic performance despite SRR-induced volumetric variability.