We propose a hierarchically structured variational inference model for accurately disentangling observable evidence of disease (e.g. brain lesions or atrophy) from subject-specific anatomy in brain MRIs. With flexible, partially autoregressive priors, our model (1) addresses the subtle and fine-grained dependencies that typically exist between anatomical and pathological generating factors of an MRI to ensure the clinical validity of generated samples; (2) preserves and disentangles finer pathological details pertaining to a patient's disease state. Additionally, we experiment with an alternative training configuration where we provide supervision to a subset of latent units. It is shown that (1) a partially supervised latent space achieves a higher degree of disentanglement between evidence of disease and subject-specific anatomy; (2) when the prior is formulated with an autoregressive structure, knowledge from the supervision can propagate to the unsupervised latent units, resulting in more informative latent representations capable of modelling anatomy-pathology interdependencies.
翻译:我们提出一个分层次结构的变异推断模型,以准确分解在脑抗体中特定对象的解剖学证据(如脑损伤或萎缩性),从而准确分解脑部中可观察到的疾病证据(如脑损伤或萎缩性)。通过灵活、部分自递退缩的前科,我们的模型(1)解决了磁共振成因的解剖和病理生成因素之间通常存在的微妙和细微的依附关系,以确保所生成样品的临床有效性;(2)保存和分解与患者疾病状态有关的细微病理细节。此外,我们试验了一种替代性培训配置,我们向一组潜伏单位提供监督。我们发现:(1) 部分受监督的潜在空间在疾病证据和特定对象解剖方面达到更高程度的分解程度;(2) 当前一种由自毁结构形成时,监督知识可以传播到不受监督的潜在单位,从而产生更知情的潜在表现,能够模拟解剖病理的相互依存。