Segmentation of Ultrasound Images by Using An Incremental Self-Organized Map

Abstract

This paper presents a new segmentation method for ultrasound images. A new incremental self-organized map is proposed for the segmentation of the ultrasound images. Elements of the feature vectors are formed by the fast Fourier transform (FFT) of image intensities in 4.4 square blocks. In this study, two neural networks for segmentation are comparatively examined: Kohonen map, and incremental self-organized map (ISOM). It is observed that ISOM gives the best classification performance with less number of nodes after a short training time.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 25, 2001
Accession Number
ADA412331

Entities

People

  • M. N. Kurnaz
  • T. Olmez
  • Z. Dokur

Organizations

  • Istanbul Technical University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Classification
  • Coefficients
  • Computer Simulations
  • Computer Vision
  • Electrical Engineering
  • Electronic Mail
  • Engineering
  • Feature Extraction
  • Learning
  • Machine Learning
  • Magnetic Resonance
  • Neural Networks
  • Segmented
  • Simulations
  • Training
  • Ultrasounds
  • Unsupervised Machine Learning

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML