Unsupervised Probabilistic Deformation Modeling for Robust Diffeomorphic Registration

TL;DR

This paper introduces an unsupervised probabilistic registration method using a CVAE that ensures diffeomorphic transformations, achieving robust, regular deformations and enabling pathological deformation modeling and disease clustering.

Contribution

It presents a novel unsupervised probabilistic registration framework with diffeomorphic constraints, improving deformation regularity and enabling pathological deformation analysis.

Findings

Achieved a mean DICE score of 78.3% on cardiac MR data.

Demonstrated comparable registration accuracy to state-of-the-art methods.

Enabled disease clustering with 70% classification accuracy.

Abstract

We propose a deformable registration algorithm based on unsupervised learning of a low-dimensional probabilistic parameterization of deformations. We model registration in a probabilistic and generative fashion, by applying a conditional variational autoencoder (CVAE) network. This model enables to also generate normal or pathological deformations of any new image based on the probabilistic latent space. Most recent learning-based registration algorithms use supervised labels or deformation models, that miss important properties such as diffeomorphism and sufficiently regular deformation fields. In this work, we constrain transformations to be diffeomorphic by using a differentiable exponentiation layer with a symmetric loss function. We evaluated our method on 330 cardiac MR sequences and demonstrate robust intra-subject registration results comparable to two state-of-the-art methods but with more regular deformation fields compared to a recent learning-based algorithm. Our method reached a mean DICE score of 78.3% and a mean Hausdorff distance of 7.9mm. In two preliminary experiments, we illustrate the model's abilities to transport pathological deformations to healthy subjects and to cluster five diseases in the unsupervised deformation encoding space with a classification performance of 70%.