An incremental neural network for tissue segmentation in ultrasound images


Kurnaz M. N. , DOKUR Z. , Olmez T.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, vol.85, no.3, pp.187-195, 2007 (Journal Indexed in SCI) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 85 Issue: 3
  • Publication Date: 2007
  • Doi Number: 10.1016/j.cmpb.2006.10.010
  • Title of Journal : COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
  • Page Numbers: pp.187-195

Abstract

This paper presents an incremental neural network (INeN) for the segmentation of tissues in ultrasound images. The performances of the INeN and the Kohonen network are investigated for ultrasound image segmentation. The elements of the feature vectors are individually formed by using discrete Fourier transform (DFT) and discrete cosine transform (DCT). The training set formed from blocks of 4 x 4 pixels (regions of interest, ROIs) on five different tissues designated by an expert is used for the training of the Kohonen network. The training set of the INeN is formed from randomly selected ROIs of 4 x 4 pixels in the image. Performances of both 2D-DFT and 2D-DCT are comparatively examined for the segmentation of ultrasound images. (c) 2006 Elsevier Ireland Ltd. All rights reserved.