Share Email Print

Proceedings Paper

Application of statistical pattern recognition and image processing in ultrasound tissue characterization
Author(s): Reza Momenan; Murray H. Loew; Robert F. Wagner; Brian S. Garra; Michael F. Insana
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper consists of two parts. The first part considers the limitations imposed by statistical properties of ultrasound images. Through this analysis the minimum detectable tumor size from an ultrasound Bscan using the current state of the art is determined the second part describes an improvement to a successful tissue-characterization algorithm that adds several image processing steps to compute the tissuecharacterization features. The inclusion of such steps will enable the tissue-characterization algorithm to take advantage of visual cues similar to those that a clinician would use to differentiate various organs and segments of the image. This in turn expands the applicability of the present tissue-characterization algorithm from multivariate to multiorgan and multidisease cases.

Paper Details

Date Published: 1 July 1990
PDF: 10 pages
Proc. SPIE 1233, Medical Imaging IV: Image Processing, (1 July 1990); doi: 10.1117/12.18906
Show Author Affiliations
Reza Momenan, George Washington Univ. (United States)
Murray H. Loew, George Washington Univ. (United States)
Robert F. Wagner, Ctr. for Devices and Radiological Health/FDA (United States)
Brian S. Garra, Georgetown Univ. Hospital (United States)
Michael F. Insana, Univ. of Kansas Medical Ctr. (United States)

Published in SPIE Proceedings Vol. 1233:
Medical Imaging IV: Image Processing
Murray H. Loew, Editor(s)

© SPIE. Terms of Use
Back to Top