Application of Improved Wild Horse Optimizer Based on Chaos Initialization in Medical Image Segmentation

In the field of auxiliary medicine, medical image segmentation is an effective diagnostic measure, but there is still room for improvement in the accuracy and efficiency of medical image segmentation. Therefore, this paper analyzes a new swarm intelligence optimization algorithm–Wild Horse optimization algorithm (WHO), which has been improved and applied in medical image segmentation. The WHO is mainly optimized by simulating the life behavior of the wild horse population, and it has the characteristics of strong optimization ability and fast convergence speed, but the WHO is easy to fall into local optimization in medical image segmentation. Therefore, this paper uses the initialization method of Logistic chaotic map to replace the random initialization scheme in the original WHO, and compares the image segmentation results with Fuzzy Wild Horse optimization algorithm (FWHO), Fuzzy Improved Fast Artificial Bee Colony and its Aggregation Algorithm (FMQABCA) and Coyote Algorithm (COA). The results show that the improved WHO has better segmentation effect and efficiency.