Clinically Plausible Pathology-Anatomy Disentanglement in Patient Brain MRI with Structured Variational Priors
This work addresses the challenge of clinically valid MRI analysis for medical imaging applications, representing an incremental improvement in disentanglement methods.
The authors tackled the problem of disentangling disease evidence from subject-specific anatomy in brain MRIs by proposing a hierarchically structured variational inference model with flexible priors, achieving higher disentanglement and more informative latent representations through partial supervision and autoregressive structures.
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.