Estimation of K distribution parameters using neural networks

Mark P Wachowiak; Renata Smolíková; Jacek M Zurada; Adel S Elmaghraby

doi:10.1109/TBME.2002.1001977

Estimation of K distribution parameters using neural networks

IEEE Trans Biomed Eng. 2002 Jun;49(6):617-20. doi: 10.1109/TBME.2002.1001977.

Authors

Mark P Wachowiak¹, Renata Smolíková, Jacek M Zurada, Adel S Elmaghraby

Affiliation

¹ Computer Science and Engineering Program, University of Louisville, KY 40292, USA. mpwach01@athena.louisville.edu

PMID: 12046708
DOI: 10.1109/TBME.2002.1001977

Abstract

The K distribution is an accurate model for ultrasonic backscatter. A neural approach is developed to estimate K distribution parameters. Accuracy and consistency of the estimates from simulated K and envelope data compare favorably with other techniques. Neural networks can potentially be used as a complementary technique for tissue characterization.

Publication types

Comparative Study
Research Support, Non-U.S. Gov't

MeSH terms

Computer Simulation
Models, Statistical*
Neural Networks, Computer*
Reproducibility of Results
Signal Processing, Computer-Assisted
Ultrasonography / methods*
Ultrasonography / statistics & numerical data