This article presents a general Bayesian learning framework for multi-modal groupwise registration on medical images. 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. Thus, groupwise registration is achieved through the solution to Bayesian inference. We propose a novel hierarchical variational auto-encoding architecture to realize the inference procedure of the latent variables, where the registration parameters can be calculated in a mathematically interpretable fashion. Remarkably, this new paradigm can learn groupwise registration in an unsupervised closed-loop self-reconstruction process, sparing the burden of designing complex intensity-based similarity measures. The computationally efficient disentangled 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 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 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.

翻译：本文提出了一种用于医学图像多模态组群配准的通用贝叶斯学习框架。该方法基于图像生成过程的概率建模，将观测图像的潜在共同解剖结构与几何变异性显式解耦为隐变量，从而通过贝叶斯推理实现组群配准。为此，我们设计了一种新颖的分层变分自编码架构来执行隐变量的推理过程，使得配准参数能以数学可解释的方式计算。值得注意的是，这一新范式能在无监督的闭环自重建过程中学习组群配准，避免了设计复杂强度相似性度量的负担。该计算高效的解耦架构本质上具有可扩展性与灵活性，支持对规模可变的图像组进行组群配准。此外，通过解耦学习推断出的结构表征能捕捉具有视觉语义的观测图像潜在解剖结构。我们在心脏、脑部和腹部医学图像四个数据集上进行了大量实验验证所提框架。结果表明，本方法在精度、效率、可扩展性与可解释性方面均优于传统基于相似性的方法。