Title :
Estimation of K distribution parameters using neural networks
Author :
Wachowiak, Mark P. ; Smolíková, Renata ; Zurada, Jacek M. ; Elmaghraby, Adel S.
Author_Institution :
Comput. Sci. & Eng. Program, Louisville Univ., KY, USA
fDate :
6/1/2002 12:00:00 AM
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.
Keywords :
acoustic signal processing; backscatter; biological tissues; biomedical ultrasonics; medical signal processing; multilayer perceptrons; parameter estimation; physiological models; ultrasonic scattering; K distribution parameters estimation; Rayleigh distribution; accurate ultrasonic backscatter model; demodulated radiofrequency signal; diagnosis; echo envelope; pathology analysis; speckle; tissue characterization technique; ultrasonography; Backpropagation; Computer science; Multilayer perceptrons; Neural networks; Probability density function; Rayleigh scattering; Shape; Signal to noise ratio; Statistics; Testing; Computer Simulation; Models, Statistical; Neural Networks (Computer); Reproducibility of Results; Signal Processing, Computer-Assisted; Ultrasonography;
Journal_Title :
Biomedical Engineering, IEEE Transactions on
DOI :
10.1109/TBME.2002.1001977
