Deep reinforcement learning in medical imaging: A literature review

TL;DR

This literature review explores how deep reinforcement learning techniques are applied to various medical imaging tasks, highlighting recent advances, categories of applications, and future research directions.

Contribution

It provides a comprehensive overview of DRL methods in medical imaging, categorizing applications and summarizing recent developments and challenges.

Findings

DRL is effective in landmark and lesion detection.

DRL aids in optimizing hyperparameters and neural architectures.

Applications span from image analysis to personalized healthcare.

Abstract

Deep reinforcement learning (DRL) augments the reinforcement learning framework, which learns a sequence of actions that maximizes the expected reward, with the representative power of deep neural networks. Recent works have demonstrated the great potential of DRL in medicine and healthcare. This paper presents a literature review of DRL in medical imaging. We start with a comprehensive tutorial of DRL, including the latest model-free and model-based algorithms. We then cover existing DRL applications for medical imaging, which are roughly divided into three main categories: (I) parametric medical image analysis tasks including landmark detection, object/lesion detection, registration, and view plane localization; (ii) solving optimization tasks including hyperparameter tuning, selecting augmentation strategies, and neural architecture search; and (iii) miscellaneous applications including surgical gesture segmentation, personalized mobile health intervention, and computational model personalization. The paper concludes with discussions of future perspectives.