Bochkarеv O.A., Zеnovich A.V., Losеv A.G. Regression Model for Diagnosis of Breast Pathology According to Microwaves Radiometry Data

http://dx.doi.org/10.15688/jvolsu1.2015.6.4

Bochkarev Oleg Andreevich 
Student, Institute of Mathematics and Information Technologies,
Volgograd State University
This email address is being protected from spambots. You need JavaScript enabled to view it. , This email address is being protected from spambots. You need JavaScript enabled to view it.
Prosp. Universitetsky, 100, 400062 Volgograd, Russian Federation

Zenovich Andrey Vasilyevich 
Senior Lecturer, Department of Fundamental Computer Science and Optimal Control,
Volgograd State University
This email address is being protected from spambots. You need JavaScript enabled to view it. , This email address is being protected from spambots. You need JavaScript enabled to view it.
Prosp. Universitetsky, 100, 400062 Volgograd, Russian Federation

Losev Alexander Georgievich 
Doctor of Physical and Mathematical Sciences, Professor,
Department of Mathematical Analysis and Function Theory,
Volgograd State University
This email address is being protected from spambots. You need JavaScript enabled to view it. , This email address is being protected from spambots. You need JavaScript enabled to view it.
Prosp. Universitetsky, 100, 400062 Volgograd, Russian Federation

Abstract. The paper by T.V. Zamechnik, A.G. Losev and E.A. Mazepa [6] set out an algorithm for obtaining highly informative diagnostic signs for breast pathology based on microwave radiometry. This paper examines the effect of the temperature at the reference points on the informative features. Obviously, the results of measurements depend on the ambient temperature. Unfortunately, the ambient temperature was not recorded during creation of the training sample. For analysis of indirect effects of ambient temperature we decided to use the temperature at control points T1 and T2. Analysis of the corresponding correlation coefficients revealed that the temperature at the control points has high direct correlation with the temperature changes in the mammary glands.
Learning sample data was pre-processed. We obtained linear regressions depending on the results of measurements of the temperature at the control points. Thereafter, we reduced the measurement results to an average temperature at reference points T1 and T2. The preprocessing of sample data resulted in increasing efficiency of some characteristic features for diagnosis and improved the information content of highly informative signs. So it improved the accuracy of the diagnostic algorithm. 
The paper attempts to use non-linear regression models which can be linearized. For the new training samples we used hyperbolic, logarithmic, power and exponential regressions. Using these types of regression doesn't give any new results because the regression lines of all kinds are almost identical within a range of patients temperature.

Key words: microwave radiometry, correlation analysis, breast screening, express diagnostics of malignant breast tumors, mammology.

Creative Commons License
Regression Model for Diagnosis of Breast Pathology According to Microwaves Radiometry Data by Bochkarеv O.A., Zеnovich A.V., Losеv A.G. is licensed under a Creative Commons Attribution 4.0 International License.

Citation in EnglishScience Journal of Volgograd State University. Mathematics. Physics. №6 (31) 2015 pp. 72-82

Attachments:
Download this file (3_Bochkaryov_etc.pdf) 3_Bochkaryov_etc.pdf
URL: https://mp.jvolsu.com/index.php/en/component/attachments/download/493
455 Downloads