Stochastic Optimisation Framework using the Core Imaging Library and Synergistic Image Reconstruction Framework for PET Reconstruction

TL;DR

This paper presents a stochastic optimization framework integrated into the open-source Core Imaging Library, enabling the development and comparison of stochastic algorithms for PET image reconstruction, demonstrating faster convergence than deterministic methods.

Contribution

The paper introduces a new stochastic optimization framework within CIL and implements five algorithms, facilitating easier development and comparison for PET reconstruction tasks.

Findings

Stochastic methods converge faster than deterministic algorithms.

Framework successfully implements five stochastic algorithms.

Comparison on simulated PET data shows efficiency gains.

Abstract

We introduce a stochastic framework into the open--source Core Imaging Library (CIL) which enables easy development of stochastic algorithms. Five such algorithms from the literature are developed, Stochastic Gradient Descent, Stochastic Average Gradient (-Am\'elior\'e), (Loopless) Stochastic Variance Reduced Gradient. We showcase the functionality of the framework with a comparative study against a deterministic algorithm on a simulated 2D PET dataset, with the use of the open-source Synergistic Image Reconstruction Framework. We observe that stochastic optimisation methods can converge in fewer passes of the data than a standard deterministic algorithm.