UNSURF: Uncertainty Quantification for Cortical Surface Reconstruction of Clinical Brain MRIs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mehta, Raghav, Gopinath, Karthik, Glocker, Ben, Iglesias, Juan Eugenio
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916828580675584
author Mehta, Raghav
Gopinath, Karthik
Glocker, Ben
Iglesias, Juan Eugenio
author_facet Mehta, Raghav
Gopinath, Karthik
Glocker, Ben
Iglesias, Juan Eugenio
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00498
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UNSURF: Uncertainty Quantification for Cortical Surface Reconstruction of Clinical Brain MRIs
Mehta, Raghav
Gopinath, Karthik
Glocker, Ben
Iglesias, Juan Eugenio
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title UNSURF: Uncertainty Quantification for Cortical Surface Reconstruction of Clinical Brain MRIs
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.00498