Integrating the Validation Incremental Neural Network and Radial-Basis Function Neural Network for Segmenting Prostate in Ultrasound Images

摘要

Prostate hyperplasia is usually found affecting male adults in developed countries. Transrectal ultrasoundgraphy (TRUS) imaging is widely used to diagnose prostate disease. Ultrasonic images are often argued with their primitive echo perturbations and speckle noise, which may confuse the physicians in inspection. Therefore, in this paper, we propose an automatic prostate segmentation system in TRUS images. The automatic segmentation system utilizes a prostate classifier which consists of Validation Incremental Neural Network and Radial-Basis Function Neural Networks for prostate segmentation. Experimental results show that the proposed method has higher accuracy than Active Contour Model (ACM).