Synergistic registration of CT-MRI brain images and retinal images: A novel approach leveraging reinforcement learning and modified artificial rabbit optimization

Abstract

Medical image registration is a pivotal application within the field of medical imaging. It entails the fusion of commonalities among data of disparate modalities into a unified coordinate system, thereby achieving complementary imaging information. This process plays a crucial role in scenarios such as accurate disease diagnosis, surgical guidance, patient monitoring, and radiological therapy. Due to the distinct characteristics exhibited by changes in the same region over time or across different modalities, swiftly and accurately identifying corresponding relationships between pre-registered images remains a formidable challenge. This paper proposes the incorporation of an enhanced Artificial Rabbits Optimization (ARO) algorithm as an agent within the framework of reinforcement learning. The method, referred to as RL-mARO, is employed for medical image registration. By utilizing Normalized Mutual Information (NMI) as a reward and penalty feedback for the similarity metric, the agent continuously adjusts and alters the learning strategies within the population, thereby progressively converging towards the correct registration direction. The contribution of reinforcement learning to ARO was validated on the IEEE CEC2020 benchmark dataset. Simultaneously, registration experiments were conducted on the multi-modal brain dataset, Retrospective Image Registration Evaluation Project (RIRE), as well as the single-modal fundus dataset, Fundus Image Registration Dataset (FIRE). The results of both registration experiments demonstrate that the RL-mARO model exhibits elevated robustness and registration accuracy.