A Line--Search--Based Stochastic Gradient Method for 3D Computed Tomography
Addresses the computational and memory bottlenecks in large-scale 3D CT reconstruction for medical imaging practitioners.
FB-LISA adapts a line-search-based stochastic gradient method for 3D CT reconstruction, using full 2D projection mini-batches to achieve significant speed-ups in early iterations without training data.
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.