# Sequentially optimized projections in X-ray imaging

arXiv: https://arxiv.org/abs/2006.12579 · HTML: https://mlsanity.com/paper/2006.12579/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2020.

## Built on by (most cited first, 6 of 6)

- [Amortized Bayesian Experimental Design for Decision-Making](https://mlsanity.com/paper/2411.02064/) (2024)
- [Bayesian Experimental Design for Computed Tomography with the Linearised Deep Image Prior](https://mlsanity.com/paper/2207.05714/) (2022)
- [Sequential Experimental Design for X-Ray CT Using Deep Reinforcement Learning](https://mlsanity.com/paper/2307.06343/) (2023)
- [Using Distance Correlation for Efficient Bayesian Optimization](https://mlsanity.com/paper/2102.08993/) (2021)
- [Dynamic Angle Selection in X-Ray CT: A Reinforcement Learning Approach to Optimal Stopping](https://mlsanity.com/paper/2503.12688/) (2025)
- [Edge-Aligned Beam Placement in Scanning Probe Tomography via Reconstruction-Free Sequential Design of Experiments](https://mlsanity.com/paper/2606.21713/) (2026)

## Abstract (arXiv)

This work applies Bayesian experimental design to selecting optimal projection geometries in (discretized) parallel beam X-ray tomography assuming the prior and the additive noise are Gaussian. The introduced greedy exhaustive optimization algorithm proceeds sequentially, with the posterior distribution corresponding to the previous projections serving as the prior for determining the design parameters, i.e. the imaging angle and the lateral position of the source-receiver pair, for the next one. The algorithm allows redefining the region of interest after each projection as well as adapting parameters in the (original) prior to the measured data. Both A and D-optimality are considered, with emphasis on efficient evaluation of the corresponding objective functions. Two-dimensional numerical experiments demonstrate the functionality of the approach.