Texture analysis of tissue structures as a task of nonlinear identification on base of wave-packet decomposition

Dmitriy V. Shutin; Alexander M. Akhmetshin

doi:10.1117/12.413805

19 January 2001 Texture analysis of tissue structures as a task of nonlinear identification on base of wave-packet decomposition

Dmitriy V. Shutin, Alexander M. Akhmetshin

Author Affiliations +

Proceedings Volume 4158, Biomonitoring and Endoscopy Technologies; (2001) https://doi.org/10.1117/12.413805
Event: EOS/SPIE European Biomedical Optics Week, 2000, Amsterdam, Netherlands

Abstract

In this work we have developed a new effective method to increase the probity of tissue structure classification based on X-Ray and X-RAY CT images. The proposed method requires much smaller resolution and it is also more sensitive to the small changes in the topology of tissue structure. As initial data, we used X-ray and X-ray CT images of coxa, affected with osteoporosis. The wave packet decompositions of a cut form the image were interpreted as an input and output of virtual non-linear system. The peculiarities of non-linear transfer characteristics were considered for performing a qualitative classification. The method helps to classify about 84% of data visually. A neuron network, which was used for classification based on this technique, has given an opportunity to classify correctly about 94% of all reviewed data. The described method was successfully applied to classification of other tissue.

Citation Download Citation

Dmitriy V. Shutin and Alexander M. Akhmetshin "Texture analysis of tissue structures as a task of nonlinear identification on base of wave-packet decomposition", Proc. SPIE 4158, Biomonitoring and Endoscopy Technologies, (19 January 2001); https://doi.org/10.1117/12.413805

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available