Title :
A methodology for modeling the distributions of medical images and their stochastic properties
Author :
Zhang, Ya-Qin ; Loew, Murray H. ; Pickholtz, Raymond L.
Author_Institution :
Dept. of Electr. & Comput. Eng., George Washington Univ., Washington, DC, USA
fDate :
12/1/1990 12:00:00 AM
Abstract :
The probabilistic distribution properties of a set of medical images are studied. It is shown that the generalized Gaussian function provides a good approximation to the distribution of AP chest radiographs. Based on this result and a goodness-of-fit test, a generalized Gaussian autoregressive model (GGAR) is proposed. Its properties and limitations are also discussed. It is expected that the GGAR model will be useful in describing the stochastic characteristics of some classes of medical images and in image data compression and other applications
Keywords :
diagnostic radiography; modelling; stochastic processes; AP chest radiographs; generalized Gaussian autoregressive model; generalized Gaussian function; goodness-of-fit test; image data compression; image stochastic properties; medical images distribution modeling; Biomedical imaging; Data compression; Entropy; Gaussian distribution; Histograms; Physics; Probability density function; Radiography; Stochastic processes; Testing;
Journal_Title :
Medical Imaging, IEEE Transactions on
