LEARNING TO SCAN: A DEEP REINFORCEMENT LEARNING APPROACH FOR PERSONALIZED SCANNING IN CT IMAGING

Abstract

Computed Tomography (CT) takes X-ray measurements on the subjects to reconstruct tomographic images. As X-ray is radioactive, it is desirable to control the total amount of dose of X-ray for safety concerns. Therefore, we can only select a limited number of measurement angles and assign each of them limited amount of dose. Traditional methods such as compressed sensing usually randomly select the angles and equally distribute the allowed dose on them. In most CT reconstruction models, the emphasize is on designing effective image representations, while much less emphasize is on improving the scanning strategy. The simple scanning strategy of random angle selection and equal dose distribution performs well in general, but they may not be ideal for each individual subject. It is more desirable to design a personalized scanning strategy for each subject to obtain better reconstruction result. In this paper, we propose to use Reinforcement Learning (RL) to learn a personalized scanning policy to select the angles and the dose at each chosen angle for each individual subject. We first formulate the CT scanning process as an Markov Decision Process (MDP), and then use modern deep RL methods to solve it. The learned personalized scanning strategy not only leads to better reconstruction results, but also shows strong generalization to be combined with different reconstruction algorithms.. In this paper, we focus on the angle and dose’s sample process in the whole computerized tomography. Due to the detector’s limitation, we have restrictions on angle and dose of X-ray. In order to get higher precision, we can select the angle and dose from the information we have got from before data collection to achieve personalize selection. After formulating the sample process to Markov Decision Process (MDP), we use Proximal Policy Optimization (PPO) algorithm from reinforcement learning combined with neural networks and successfully get higher precision in the CT reconstruct process.