Empirical Bayesian Mixture Models for Medical Image Translation
This work addresses medical image translation for clinical applications, but it appears incremental as it builds on existing probabilistic models for handling missing data.
The paper tackled the problem of generating missing medical imaging modalities from existing ones using an interpretable generative model, achieving promising results in three clinically relevant scenarios by predicting missing MR contrasts and CT images from one or a few MR contrasts with training on a small number of subjects.
Automatically generating one medical imaging modality from another is known as medical image translation, and has numerous interesting applications. This paper presents an interpretable generative modelling approach to medical image translation. By allowing a common model for group-wise normalisation and segmentation of brain scans to handle missing data, the model allows for predicting entirely missing modalities from one, or a few, MR contrasts. Furthermore, the model can be trained on a fairly small number of subjects. The proposed model is validated on three clinically relevant scenarios. Results appear promising and show that a principled, probabilistic model of the relationship between multi-channel signal intensities can be used to infer missing modalities -- both MR contrasts and CT images.