Abstract: Intelligent medical image processing is an important research direction in the field of medical image applications. Traditional medical image analysis is often open-loop, and the image segmentation is independent of the image recognition with low intelligence, which requires inspectors with higher skill level. In consideration of these facts, reinforcement learning is applied to blood cell image, which use the blood cell features information as feedback for the image segmentation and evaluate the segmentation results in order to realize the closed-loop intelligent blood cell image segmentation.


Key words: medical image segmentation, reinforcement learning, blood cell features, intelligent