BInGo: Bayesian Intrinsic Groupwise Registration via Explicit Hierarchical Disentanglement

TL;DR

BInGo introduces a scalable, unsupervised hierarchical Bayesian deep learning framework for multimodal groupwise medical image registration, effectively disentangling structural representations to improve accuracy and efficiency across large image groups.

Contribution

The paper presents a novel variational auto-encoder with a unique posterior for disentangling structural and spatial features in multimodal registration, enabling scalable and accurate groupwise alignment.

Findings

Outperforms existing methods in accuracy and efficiency

Effective on large-scale datasets with over 1300 images

Reduces computational costs significantly

Abstract

Multimodal groupwise registration aligns internal structures in a group of medical images. Current approaches to this problem involve developing similarity measures over the joint intensity profile of all images, which may be computationally prohibitive for large image groups and unstable under various conditions. To tackle these issues, we propose BInGo, a general unsupervised hierarchical Bayesian framework based on deep learning, to learn intrinsic structural representations to measure the similarity of multimodal images. Particularly, a variational auto-encoder with a novel posterior is proposed, which facilitates the disentanglement learning of structural representations and spatial transformations, and characterizes the imaging process from the common structure with shape transition and appearance variation. Notably, BInGo is scalable to learn from small groups, whereas being tested for large-scale groupwise registration, thus significantly reducing computational costs. We compared BInGo with five iterative or deep learning methods on three public intrasubject and intersubject datasets, i.e. BraTS, MS-CMR of the heart, and Learn2Reg abdomen MR-CT, and demonstrated its superior accuracy and computational efficiency, even for very large group sizes (e.g., over 1300 2D images from MS-CMR in each group).