PRISM: A 3D Probabilistic Neural Representation for Interpretable Shape Modeling
This work addresses the need for interpretable shape modeling with spatially varying uncertainties in healthcare research, offering a novel method for analyzing anatomical changes.
The authors tackled the problem of modeling anatomical shape evolution with covariates by introducing PRISM, a framework that combines implicit neural representations with statistical shape analysis to provide spatially continuous mean and uncertainty estimates, achieving strong performance across synthetic and clinical datasets.
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.