Pathologic region detection algorithm for prostate ultrasonic image based on PCNN

Authors:
Beidou Zhang;Yide Ma;Dongmei Lin;Liwen Zhang
Affiliations:
School of Information Science & Engineering, Lanzhou University, Lanzhou, China;School of Information Science & Engineering, Lanzhou University, Lanzhou, China;School of Information Science & Engineering, Lanzhou University, Lanzhou, China;B-Ultrasonic room of People's Hospital of Gansu Province, Lanzhou, China
Venue:
FAW'07 Proceedings of the 1st annual international conference on Frontiers in algorithmics
Year:
2007

Citing 5
Cited 0

Digital Image Processing

Digital Image Processing
Image Processing Using Pulse-Coupled Neural Networks

Image Processing Using Pulse-Coupled Neural Networks
Feature linking via synchronization among distributed assemblies: Simulations of results from cat visual cortex

Neural Computation
Automated liver detection in ultrasound images

CIVR'05 Proceedings of the 4th international conference on Image and Video Retrieval
PCNN models and applications

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

It is quite important and difficult for doctors to detect pathologic regions of prostate ultrasonic images. An automated region detection algorithm is proposed to solve this problem, especially for ultrasonic images containing all kinds of noise and speckle. First, all the pixels of an ultrasonic image are fired by Pulse Coupled Neural Network (PCNN). Then after being processed by morphological closing, binary reversing and region labeling, the seeds are detected automatically using PCNN, by which the region of interest (ROI) of the ultrasonic image is detected by Region Growing. In the end, we code the ROI by pseudo-color. Detected pathologic regions can be used for further clinical inspection and quantitative analysis of ultrasonic images.