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

2023-07-12 · Tianyuan Wang, Felix Lucka, Tristan van Leeuwen

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.

📄 PDF Abstract BibTeX arXiv:2307.06343

Code (1)

tianyuan1wang/seqanglerl 공식 구현 pytorch

Tasks

3D ReconstructionComputed Tomography (CT)Deep Reinforcement LearningExperimental Designreinforcement-learning

Performance Comparisons of Reinforcement Learning Algorithms for Sequential Experimental Design

2025-03-07 · Yasir Zubayr Barlas, Kizito Salako

Recent developments in sequential experimental design look to construct a policy that can efficiently navigate the design space, in a way that maximises the expected information gain. Whilst there is work on achieving tr…

Experimental Design Navigate reinforcement-learning Reinforcement Learning

Sequential Bayesian experimental designs via reinforcement learning

2022-02-14 · Hikaru Asano

Bayesian experimental design (BED) has been used as a method for conducting efficient experiments based on Bayesian inference. The existing methods, however, mostly focus on maximizing the expected information gain (EIG)…

Bayesian Inference Decision Making Experimental Design reinforcement-learning+3

Variational Sequential Optimal Experimental Design using Reinforcement Learning

2023-06-17 · Wanggang Shen, Jiayuan Dong, Xun Huan

We present variational sequential optimal experimental design (vsOED), a novel method for optimally designing a finite sequence of experiments within a Bayesian framework with information-theoretic criteria. vsOED employ…

Experimental Design reinforcement-learning Reinforcement Learning

Bayesian Sequential Optimal Experimental Design for Nonlinear Models Using Policy Gradient Reinforcement Learning

2021-10-28 · Wanggang Shen, Xun Huan

We present a mathematical framework and computational methods to optimally design a finite number of sequential experiments. We formulate this sequential optimal experimental design (sOED) problem as a finite-horizon par…

Experimental Design reinforcement-learning Reinforcement Learning (RL)

Optimizing Sequential Experimental Design with Deep Reinforcement Learning

2022-02-02 · Tom Blau, Edwin V. Bonilla, Iadine Chades, Amir Dezfouli

Bayesian approaches developed to solve the optimal design of sequential experiments are mathematically elegant but computationally challenging. Recently, techniques using amortization have been proposed to make these Bay…

Deep Reinforcement Learning Experimental Design reinforcement-learning Reinforcement Learning+1