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

2025/05/31 by Raghav Mehta, Mehta, Raghav, Karthik Gopinath +5
Medicine · Engineering · Biochemistry, Genetics and Molecular Biology · #Medical Imaging Techniques and Applications #Advanced X-ray and CT Imaging #Cell Image Analysis Techniques

paper · pdf · doi:10.48550/arxiv.2506.00498

Abstract

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: (i)~enable effective automated quality control of surface reconstructions at the subject-, parcel-, mesh node-level; and (ii)~improve performance on a downstream Alzheimer's disease classification task.

Citations

• Hierarchical Uncertainty Estimation for Learning-based Registration in Neuroimaging
• Recon-all-clinical: Cortical surface reconstruction and analysis of heterogeneous clinical brain MRI
• A review of uncertainty quantification in medical image analysis: probabilistic and non-probabilistic methods
• Improving Image-Based Precision Medicine with Uncertainty-Aware Causal Models
• Cortical analysis of heterogeneous clinical brain MRI scans for large-scale neuroimaging studies
• Uncertainty-informed Mutual Learning for Joint Medical Image Classification and Segmentation
• Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks
• Vox2Cortex: Fast Explicit Reconstruction of Cortical Surfaces from 3D\n MRI Scans with Geometric Deep Neural Networks
• CortexODE: Learning Cortical Surface Reconstruction by Neural ODEs
• DeepCSR: A 3D Deep Learning Approach for Cortical Surface Reconstruction
• Sampling possible reconstructions of undersampled acquisitions in MR imaging
• PHiSeg: Capturing Uncertainty in Medical Image Segmentation
• Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis\n Lesion Detection and Segmentation
• Understanding Measures of Uncertainty for Adversarial Example Detection
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• U-Net: Convolutional Networks for Biomedical Image Segmentation

Related

• Cortical analysis of heterogeneous clinical brain MRI scans for large-scale neuroimaging studies
• Synthesizing longitudinal cortical thickness estimates with a flexible and hierarchical multivariate measurement-error model
• Recon-all-clinical: Cortical surface reconstruction and analysis of heterogeneous clinical brain MRI
• End-to-end Cortical Surface Reconstruction from Clinical Magnetic Resonance Images
• NPB-REC: Non-parametric Assessment of Uncertainty in Deep-learning-based MRI Reconstruction from Undersampled Data