Deep kernel representations of latent space features for low-dose PET-MR imaging robust to variable dose reduction
This addresses the challenge of producing quantitatively accurate PET images from low-dose signals for medical imaging applications, with incremental improvements in robustness to unseen dose reductions.
The paper tackles the problem of unreliable low-dose PET image reconstruction with deep learning by introducing a method that models deep latent space features using a robust kernel representation, achieving significantly improved performance on out-of-distribution dose reduction factors from ×10 to ×1000 compared to conventional methods.
Low-dose positron emission tomography (PET) image reconstruction methods have potential to significantly improve PET as an imaging modality. Deep learning provides a promising means of incorporating prior information into the image reconstruction problem to produce quantitatively accurate images from compromised signal. Deep learning-based methods for low-dose PET are generally poorly conditioned and perform unreliably on images with features not present in the training distribution. We present a method which explicitly models deep latent space features using a robust kernel representation, providing robust performance on previously unseen dose reduction factors. Additional constraints on the information content of deep latent features allow for tuning in-distribution accuracy and generalisability. Tests with out-of-distribution dose reduction factors ranging from $\times 10$ to $\times 1000$ and with both paired and unpaired MR, demonstrate significantly improved performance relative to conventional deep-learning methods trained using the same data. Code:https://github.com/cameronPain