From Images to Probabilistic Anatomical Shapes: A Deep Variational Bottleneck Approach
- 16 September 2022
- book chapter
- Published by Springer Nature
- Vol. 13432, 474-484
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 of 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 an accuracy improvement and better calibrated aleatoric uncertainty estimates than state-of-the-art methods. Keywords Uncertainty quantification Statistical shape modeling Bayesian deep learningKeywords
All Related Versions
This publication has 18 references indexed in Scilit:
- ShapeWorks2017
- Quantitative comparison of cortical bone thickness using correspondence-based shape modeling in patients with cam femoroacetabular impingementJournal of Orthopaedic Research, 2016
- DeepShape: Deep-Learned Shape Descriptor for 3D Shape RetrievalIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- 3D Deep Learning for Efficient and Robust Landmark Detection in Volumetric Data2015
- Computational Planning in Facial SurgeryFacial Plastic Surgery, 2015
- Statistical shape and appearance models of bonesBone, 2014
- Statistical shape modeling of cam femoroacetabular impingementJournal of Orthopaedic Research, 2013
- Shape Modeling and Analysis with Entropy-Based Particle Systems2007
- Probabilistic visual learning for object representationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997