PRISM: A 3D Probabilistic Neural Representation for Interpretable Shape Modeling

TL;DR

PRISM introduces a probabilistic neural framework for interpretable 3D shape modeling that captures spatially varying uncertainties and shape evolution in healthcare applications.

Contribution

It combines implicit neural representations with uncertainty-aware statistical analysis, providing a novel closed-form Fisher Information metric for local uncertainty quantification.

Findings

Effective on synthetic and clinical datasets

Provides spatially continuous uncertainty estimates

Achieves strong performance across diverse shape modeling tasks

Abstract

Understanding how anatomical shapes evolve in response to developmental covariates and quantifying their spatially varying uncertainties is critical in healthcare research. Existing approaches typically rely on global time-warping formulations that ignore spatially heterogeneous dynamics. We introduce PRISM, a novel framework that bridges implicit neural representations with uncertainty-aware statistical shape analysis. PRISM models the conditional distribution of shapes given covariates, providing spatially continuous estimates of both the population mean and covariate-dependent uncertainty at arbitrary locations. A key theoretical contribution is a closed-form Fisher Information metric that enables efficient, analytically tractable local temporal uncertainty quantification via automatic differentiation. Experiments on three synthetic datasets and one clinical dataset demonstrate PRISM's strong performance across diverse tasks within a unified framework, while providing interpretable and clinically meaningful uncertainty estimates.