Title :
Rough location of the prostate TRUS images
Author :
Jianping Song;Yongtao Shi
Author_Institution :
College of Science and Technology, China Three Gorges University, Yichang, Hubei Province, China 443002
Abstract :
The initialization is considerably important for automatic segmentation of transrectal ultrasound (TRUS) images. This paper presents a novel initialization method based on narrow band boundary feature which can be used to roughly locate the boundary of interest in prostate TRUS images. The proposed method is able to automatically locating the edge in very few time and experimental results showed that it is considerably robust.
Keywords :
"Shape","Feature extraction","Image segmentation","Image edge detection","Ultrasonic imaging","Robustness","Image resolution"
Conference_Titel :
Information and Automation, 2015 IEEE International Conference on
DOI :
10.1109/ICInfA.2015.7279410
