Sequential Experimental Design for X-Ray CT Using Deep Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning approach to optimize sequential X-ray CT scan angles, enabling efficient, high-quality 3D reconstructions from limited data in real-time.

Contribution

It formulates the optimal experimental design problem as a Bayesian POMDP and trains a policy offline using Actor-Critic methods for online angle selection in CT.

Findings

The RL-based policy effectively identifies informative scan angles.

The approach reduces the number of projections needed for quality reconstructions.

Performance demonstrated on synthetic 2D tomography data.

Abstract

In X-ray Computed Tomography (CT), projections from many angles are acquired and used for 3D reconstruction. To make CT suitable for in-line quality control, reducing the number of angles while maintaining reconstruction quality is necessary. Sparse-angle tomography is a popular approach for obtaining 3D reconstructions from limited data. To optimize its performance, one can adapt scan angles sequentially to select the most informative angles for each scanned object. Mathematically, this corresponds to solving an optimal experimental design (OED) problem. OED problems are high-dimensional, non-convex, bi-level optimization problems that cannot be solved online, i.e., during the scan. To address these challenges, we pose the OED problem as a partially observable Markov decision process in a Bayesian framework, and solve it through deep reinforcement learning. The approach learns efficient non-greedy policies to solve a given class of OED problems through extensive offline training rather than solving a given OED problem directly via numerical optimization. As such, the trained policy can successfully find the most informative scan angles online. We use a policy training method based on the Actor-Critic approach and evaluate its performance on 2D tomography with synthetic data.