Deep Bayesian Inversion
This work addresses the challenge of making Bayesian inversion computationally efficient for time-critical 3D imaging applications in clinical settings, representing a domain-specific advancement.
The paper tackles the computational infeasibility of Bayesian inversion for realistic clinical imaging by introducing two deep learning methods, achieving promising performance in 3D helical CT image reconstruction for detecting liver dark spots in cancer patients.
Characterizing statistical properties of solutions of inverse problems is essential for decision making. Bayesian inversion offers a tractable framework for this purpose, but current approaches are computationally unfeasible for most realistic imaging applications in the clinic. We introduce two novel deep learning based methods for solving large-scale inverse problems using Bayesian inversion: a sampling based method using a WGAN with a novel mini-discriminator and a direct approach that trains a neural network using a novel loss function. The performance of both methods is demonstrated on image reconstruction in ultra low dose 3D helical CT. We compute the posterior mean and standard deviation of the 3D images followed by a hypothesis test to assess whether a "dark spot" in the liver of a cancer stricken patient is present. Both methods are computationally efficient and our evaluation shows very promising performance that clearly supports the claim that Bayesian inversion is usable for 3D imaging in time critical applications.