In Vivo Study of Online Liver Tissue Classification Based on Envelope Power Spectrum Analysis

Abstract

An ultrasonic imaging and signal analysis system, combining a 3.5 MHz linear array B-scanner and an array processor, has been realized for a clinical liver tissue classification study. Based on the complete unprocessed rf data set of a real time B-image, local envelope power spectra averaged over interactively defined regions are computed. These spectra are partially corrected for several tissue type independent effects that affect comparability. A library containing the in vivo data of 65 patients with known liver tissue states in three groups (normal, cirrhotic, fat) was built up. An algorithm based on numerical optimization of parametrized spectrum characteristics combined with a k-nearest-neighbors classifier, applied to the library, leads to correct classification rates of 85.8 to 87.5 percent in discriminating pathological from normal tissue states. The method can be used for k-weighted color coded tissue type imaging with acceptable spatial resolution.

Keywords

Diffuse liver disease kNN-classifier numerical optimization pattern recognition power spectrum analysis tissue classification tissue type imaging ultrasound

Get full access to this article

View all access options for this article.

References

Ophir

Shawker

T.H.

Maklad

N.F.

Miller

J.G.

Flax

S.W.

Narayana

P.A.

Jones

J.P.

Attenuation estimation in reflection: progress and prospects, Ultrasonic Imaging 6, 349–395 (1984).

Chen

C.F.

Robinson

D.E.

Wilson

L.S.

Griffith

K.A.

Manokaran

Doust

Clinical sound speed measurements in liver and spleen in vivo, Ultrasonic Imaging 9, 221–235 (1987).

Lizzi

F.L.

Ostromogilsky

Feleppa

E.J.

Rorke

M.C.

Yaremko

M.M.

Relationship of ultrasonic spectral parameters to features of tissue microstructure, IEEE Trans. Ultrason. Ferroelec. Frequ. Contr. UFFC-33, 319–329 (1987).

Insana

M.F.

Wagner

R.F.

Brown

D.G.

Hall

T.J.

Describing small scale structure in random media using pulse echo ultrasound, J. Acoust. Soc. Am. 87, 179–192 (1990).

Waag

R.C.

A review of tissue characterization from ultrasonic scattering, IEEE Trans. Biomed. Eng. BME-31, 884–893 (1984).

Insana

M.F.

Wagner

R.F.

Garra

B.S.

Momenan

Shawker

T.H.

Pattern recognition methods for optimizing multivariate tissue signatures in diagnostic ultrasound, Ultrasonic Imaging 8, 165–180 (1986).

Oosterveld

B.J.

Thijssen

J.M.

Hartman

P.C.

Rosenbusch

G.J.E.

Ultrasound Attenuation and B-mode Texture Analysis of Diffuse Liver Disease, in Ultrasonic Tissue Characterization and Echographic Imaging. Vol. 1, Thijssen

J.M.

, ed., Proc. 8th EC Workshop Nijmegen 1987 (Office for Off. Publ. of the EC, Brussels, 1989).

Wagner

R.F.

Insana

M.F.

Brown

D.G.

Statistical properties of radio-frequency and envelope-detected signals with applications to medical ultrasound. J. Opt. Soc. Am. A4, 910–922 (1987).

Wells

P.N.T.

Biomedical Ultrasonics. Chap. 4 (Academic Press, London / New York, 1977).

10.

Claesson

Salomonsson

Frequency- and depth-dependent compensation of ultrasonic signals, IEEE Trans. Ultrason. Ferroelec. Frequ. Cont. UFFC-35, 582–592 (1988).

11.

Gammel

P.M.

Improved ultrasonic detection using the analytic signal magnitude, Ultrasonics 19, 73–76 (1981).

12.

Harris

F.J.

On the use of windows for harmonic analysis with the discrete fourier transform, Proc. IEEE 66, 51–83 (1987).

13.

Rabiner

L.R.

Gold

Theory and Application of Digital Signal Processing, Chap. 6 (Prentice-Hall, Englewood Cliffs, NJ, 1975).

14.

Kader

K.L.

Hubbard

Carroll

Hepatic ultrasonic tissue characterization of video image data, Investigative Radiology 25, 1091–1094.

15.

Patrick

E.A.

Fundamentals of Pattern Recognition. Chap. 4 (Prentice Hall, Englewood Cliffs, NJ, 1972).