Automatic prostate boundary recognition in sonographic images using feature model and genetic algorithm

This paper describes the development of a model based boundary recognition system for transrectal prostate ultrasonographic images. It consists of two techniques: boundary modeling and boundary searching with model constraint s. To achieve higher specificity of the model, a method called feature mode ling is derived from the existing point distribution modeling method. To im prove the robustness of the searching technique, the genetic algorithm is u sed. Incremental genetic algorithm with crowding replacement and binary str ing chromosome type was found experimentally to give good search results. I t was shown that the system could recognize the boundary with considerable accuracy and consistency within a few minutes in transrectal ultrasonograph ic images taken from approximate middle position of the prostate.