Share Email Print
cover

Proceedings Paper

Tissue characterization by texture analysis of ultrasonic images
Author(s): Olivier Basset; Zhigang Sun; Gerard Gimenez
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Ultrasonic B-scan images present a particular texture known as `speckle' which may reveal information relative to the investigated tissue structure. The present work is devoted to the discrimination of various prostatic tissues (normal tissue, benign prostatic hypertrophy, and cancer). This is done on ultrasonic scans by means of texture analysis. Three methods have been implemented: the autocorrelation function and the co-occurrence matrices, measuring second order statistics and the gray level run lengths matrices. Parameters derived from the co-occurrence matrices provides a fairly good tissue signature. The processing of 37 images gives a 78% score of samples classified with success. Note that the various images can not be visually discriminated. However, such results are obtained when wide regions of interest are investigated (64 X 64 pixels), but they are less significant when the sample size decreases, that is when the pathological area is very small.

Paper Details

Date Published: 12 January 1993
PDF: 12 pages
Proc. SPIE 1771, Applications of Digital Image Processing XV, (12 January 1993); doi: 10.1117/12.139102
Show Author Affiliations
Olivier Basset, Institut National des Sciences Appliquees de Lyon (France)
Zhigang Sun, Institut National des Sciences Appliquees de Lyon (France)
Gerard Gimenez, Institut National des Sciences Appliquees de Lyon (France)


Published in SPIE Proceedings Vol. 1771:
Applications of Digital Image Processing XV
Andrew G. Tescher, Editor(s)

© SPIE. Terms of Use
Back to Top