Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration

Abstract

This article presents a general Bayesian learning framework for multi-modal groupwise image registration. The method builds on probabilistic modelling of the image generative process, where the underlying common anatomy and geometric variations of the observed images are explicitly disentangled as latent variables. Therefore, groupwise image registration is achieved via hierarchical Bayesian inference. We propose a novel hierarchical variational auto-encoding architecture to realise the inference procedure of the latent variables, where the registration parameters can be explicitly estimated in a mathematically interpretable fashion. Remarkably, this new paradigm learns groupwise image registration in an unsupervised closed-loop self-reconstruction process, sparing the burden of designing complex image-based similarity measures. The computationally efficient disentangled network architecture is also inherently scalable and flexible, allowing for groupwise registration on large-scale image groups with variable sizes. Furthermore, the inferred structural representations from multi-modal images via disentanglement learning are capable of capturing the latent anatomy of the observations with visual semantics. Extensive experiments were conducted to validate the proposed framework, including four different datasets from cardiac, brain, and abdominal medical images. The results have demonstrated the superiority of our method over conventional similarity-based approaches in terms of accuracy, efficiency, scalability, and interpretability.

References in corpus (12)

• A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI
• VoxelMorph: A Learning Framework for Deformable Medical Image Registration
• Normalizing Flows: An Introduction and Review of Current Methods
• A Deep Learning Framework for Unsupervised Affine and Deformable Image Registration
• CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentation
• TransMorph: Transformer for unsupervised medical image registration
• Weakly-Supervised Convolutional Neural Networks for Multimodal Image Registration
• Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces
• Multivariate mixture model for myocardium segmentation combining multi-source images
• Hetero-Modal Variational Encoder-Decoder for Joint Modality Completion and Segmentation
• ModeT: Learning Deformable Image Registration via Motion Decomposition Transformer
• $\mathcal{X}$-Metric: An N-Dimensional Information-Theoretic Framework for Groupwise Registration and Deep Combined Computing