A Line--Search--Based Stochastic Gradient Method for 3D Computed Tomography

TL;DR

This paper presents FB-LISA, a stochastic gradient method with line search for efficient 3D CT reconstruction, leveraging mini-batches of full projections to improve speed without training data.

Contribution

It introduces a novel forward-backward line-search stochastic gradient algorithm tailored for large-scale volumetric CT reconstruction, combining deep learning concepts without requiring prior training.

Findings

Demonstrates significant speed-ups in early iterations.

Preserves physical acquisition structure with mini-batches.

Addresses high computational and memory demands of 3D CT.

Abstract

We introduce FB-LISA, a forward-backward (FB) generalization of a recently proposed line-search-based stochastic gradient algorithm to address the imaging problem of volumetric reconstruction in Computed Tomography, a substantially high demanding problem, which involves orders of magnitude of data, a high computational burden for forward and backprojection, and memory requirements that push current GPU architectures to their limits. Our formulation employs stochastic mini-batches composed of full 2D projections, preserving the physical structure of the acquisition process while enabling significant speed-ups during early iterations. The resulting method demonstrates how concepts traditionally associated with deep learning can be repurposed to accelerate large-scale inverse problems, without relying on training data or learned priors.