Efficient Conformal Volumetry for Template-Based Segmentation

TL;DR

This paper introduces ConVOLT, a conformal prediction framework that provides efficient and accurate volumetric uncertainty quantification in template-based medical image segmentation by leveraging deformation field properties.

Contribution

ConVOLT is the first method to condition conformal calibration on deformation space features for volumetric UQ in template-based segmentation.

Findings

ConVOLT achieves target coverage with tighter intervals than output-space methods.

It effectively utilizes deformation properties for uncertainty quantification.

Demonstrated across multiple datasets and registration techniques.

Abstract

Template-based segmentation, a widely used paradigm in medical imaging, propagates anatomical labels via deformable registration from a labeled atlas to a target image, and is often used to compute volumetric biomarkers for downstream decision-making. While conformal prediction (CP) provides finite-sample valid intervals for scalar metrics, existing segmentation-based uncertainty quantification (UQ) approaches either rely on learned model features, often unavailable in classic template-based pipelines, or treat the registration process as a black box, resulting in overly conservative intervals when applied directly in output space. We introduce ConVOLT, a CP framework that achieves efficient volumetric UQ by conditioning calibration on properties of the estimated deformation field from template-based segmentation. ConVOLT calibrates a learned volumetric scaling factor from deformation space features. We evaluate ConVOLT on template-based segmentation tasks involving global, regional, and label volumetry across multiple datasets and registration methods. ConVOLT achieves target coverage while producing substantially tighter intervals than output-space conformal baselines. Our work paves way to exploit the registration process for efficient UQ in medical imaging pipelines.