From Images to Probabilistic Anatomical Shapes: A Deep Variational Bottleneck Approach

TL;DR

This paper introduces a deep variational bottleneck framework for probabilistic anatomical shape modeling from 3D images, improving accuracy and uncertainty calibration over existing PCA-based methods.

Contribution

It proposes a novel variational information bottleneck approach that learns shape representations directly from images without predefined descriptors, enhancing flexibility and scalability.

Findings

Improved shape prediction accuracy.

Better calibrated aleatoric uncertainty estimates.

Enhanced generalization with limited data.

Abstract

Statistical shape modeling (SSM) directly from 3D medical images is an underutilized tool for detecting pathology, diagnosing disease, and conducting population-level morphology analysis. Deep learning frameworks have increased the feasibility of adopting SSM in medical practice by reducing the expert-driven manual and computational overhead in traditional SSM workflows. However, translating such frameworks to clinical practice requires calibrated uncertainty measures as neural networks can produce over-confident predictions that cannot be trusted in sensitive clinical decision-making. Existing techniques for predicting shape with aleatoric (data-dependent) uncertainty utilize a principal component analysis (PCA) based shape representation computed in isolation from the model training. This constraint restricts the learning task to solely estimating pre-defined shape descriptors from 3D images and imposes a linear relationship between this shape representation and the output (i.e., shape) space. In this paper, we propose a principled framework based on the variational information bottleneck theory to relax these assumptions while predicting probabilistic shapes of anatomy directly from images without supervised encoding of shape descriptors. Here, the latent representation is learned in the context of the learning task, resulting in a more scalable, flexible model that better captures data non-linearity. Additionally, this model is self-regularized and generalizes better given limited training data. Our experiments demonstrate that the proposed method provides improved accuracy and better calibrated aleatoric uncertainty estimates than state-of-the-art methods.