Bayesian Experimental Design for Computed Tomography with the Linearised Deep Image Prior

• DOI: 10.48550/arxiv.2207.05714
• Publication Date: 2022-01-01
• Authors: Barbano, Riccardo; Leuschner, Johannes; Antorán, Javier; Jin, Bangti; Hernández-Lobato,...
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; 03 medical and health sciences; 0302 clinical medicine; Computer Vision and Pattern Recognition (cs.CV); Computer Science - Computer Vision and Pattern Recognition; Machine Learning (cs.LG)

We investigate adaptive design based on a single sparse pilot scan for generating effective scanning strategies for computed tomography reconstruction. We propose a novel approach using the linearised deep image prior. It allows incorporating information from the pilot measurements into the angle selection criteria, while maintaining the tractability of a conjugate Gaussian-linear model. On a synthetically generated dataset with preferential directions, linearised DIP design allows reducing the number of scans by up to 30% relative to an equidistant angle baseline.