UNSURF: Uncertainty Quantification for Cortical Surface Reconstruction of Clinical Brain MRIs
This addresses uncertainty quantification for medical imaging analysis, particularly in clinical settings with varied scan parameters, though it appears incremental as it builds on existing surface reconstruction methods.
The paper tackles the problem of quantifying uncertainty in cortical surface reconstruction from clinical brain MRI scans, showing that traditional uncertainty measures are unsuitable and that their proposed UNSURF method correlates well with ground truth errors and improves Alzheimer's disease classification performance.
We propose UNSURF, a novel uncertainty measure for cortical surface reconstruction of clinical brain MRI scans of any orientation, resolution, and contrast. It relies on the discrepancy between predicted voxel-wise signed distance functions (SDFs) and the actual SDFs of the fitted surfaces. Our experiments on real clinical scans show that traditional uncertainty measures, such as voxel-wise Monte Carlo variance, are not suitable for modeling the uncertainty of surface placement. Our results demonstrate that UNSURF estimates correlate well with the ground truth errors and: \textit{(i)}~enable effective automated quality control of surface reconstructions at the subject-, parcel-, mesh node-level; and \textit{(ii)}~improve performance on a downstream Alzheimer's disease classification task.