A new edge detection algorithm in TRUS images

  • Authors:

  • Ali Rafiee;Ahad Salimi;Ali Reza Roosta

  • Affiliations:

  • Islamic Azad University, Kazeroun, Iran;Islamic Azad University, Najafabad, Iran;Shiraz University of Technology, shiraz, iran

  • Venue:
  • AIKED'09 Proceedings of the 8th WSEAS international conference on Artificial intelligence, knowledge engineering and data bases
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

In many diagnostic and treatment procedures for prostate disease accurate detection of prostate boundaries in transrectal ultrasound (TRUS) images is required. This is a challenging and difficult task due to weak prostate boundaries, speckle noise and the short range of gray levels. In this paper a novel edge detection method for automatic prostate segmentation in TRUS images is presented. This method involves preprocessing (edge preserving noise reduction and smoothing) and prostate segmentation. The speckle reduction has been achieved by using stick filter and top-hat transform has been implemented for smoothing. A feed forward neural network and local binary pattern together have been use to find a point inside prostate object. Finally the boundary of prostate is extracted by the inside point and an active contour algorithm. A numbers of experiments are conducted to validate this method and results showed that this new algorithm extracted the prostate boundary with MSE less than 3.9% relative to boundary provided manually by physicians.