Visual analytics in digital biomedicine on the example of the breast cancer diagnostics quality

О.А. Troyanozhko, I.D. Kolesin

Abstract


The optimization of the breast cancer diagnostics in considered in this paper. The issue of classifying a tumor as benign or malignant is being resolved. Histochemistry of breast tumor punctates is performed using a fine-needle aspiration puncture. Next, a digital analysis of images of cell nuclei in micrographs obtained from sections of tissue pieces is performed. Working within the framework of the standard approaches of medical diagnostics, the authors carried out two stages: diagnostic features ranking was done at the first stage, and then patients classification was fulfilled at the second stage. A discrete error function was used to register the number of incorrectly diagnosed patients. The authors studied the geometric characteristics of the behavior of a discrete error function in the parameter space of a linear discriminant function. We developed and programmed an algorithm for movement to a minimum, visually showing in 2D and 3D the dynamics of changes in the error function values. As a result, it was shown that a sufficiently reliable diagnosis with an accuracy of 94.73% can be carried out based only by two diagnostic features.


Full Text:

PDF (Russian)

References


VOZ https://www.who.int/topics/cancer/breastcancer/ru/index1.html (data obrashhenija: 10.02.2019).

Zhuravlev, Ju.I. Raspoznavanie. Matematicheskie metody. Programmnaja sistema. Prakticheskie primenenija / Ju.I. Zhuravlev, V.V. Rjazanov, O.V. Sen'ko. – M.: Fazis, 2006. – 176 s.

Bondarenko, N.N. Algoritm vybora kon"junkcij dlja logicheskih metodov raspoznavanija / N.N. Bondarenko, Ju.I. Zhuravlev // Zh. vychisl. matem. i matem. fiz. – 2012. – # 52. – S. 746-749.

Vapnik, V.N. Teorija raspoznavanija obrazov / V.N. Vapnik, A.Ja. Chervonenkis. – M.: Nauka, 1974. – 416 s.

Barnhill, S. Gene selection for cancer classification using support vector machines / S. Barnhill, I. Guyon, V. Vapnik // Machine learning, 2002. – Vol. 46. –pp. 389–422.

Vapnik, V. Estimation of Dependences Based on Empirical Data / V. Vapnik. – Springer, New York, 2006. – 505 pp.

Vapnik V. Statistical learning theory / V. Vapnik. – Wiley, New York, 1998. – 768 pp.

Zagorujko, N.G. Prikladnye metody analiza dannyh i znanij / N.G. Zagorujko.– Novosibirsk: IM SO RAN, 1999.– 270 s.

Bukin A.D. New Minimization Strategy for Non-Smooth Functions. Novosibirsk, 1997. 24 p.

Genkin, A.A. Novaja informacionnaja tehnologija analiza medicinskih dannyh: programmnyj kompleks OMIS / A.A. Genkin. – SPb.: Politehnika, 1999. – 191 s.

Dem'janov, V.F. Prognozirovanie jeffektivnosti himioterapii pri lechenii onkologicheskih zabolevanij / V.F. Dem'janov, V.V. Dem'janova, A.V. Kokorina, V.M. // Vestnik Sankt-Peterburgskogo universiteta, Prikladnaja matematika. – 2006 . – # 4. – c. 30-36.

Djuk V.A. Instrumental'nye sredstva intellektual'nogo analiza dannyh. – Izd-vo RGPU im. A.I. Gercena, 2012. – 161 s.

Djuk, V.A. Informacionnye tehnologii v mediko-biologicheskih issledovanijah / V. Djuk, V. Jemanujel'. – SPb.: Piter, 2003. – 528 s.

Kalitkin, N.N. Chislennye metody / N.N. Kalitkin. – M.: Nauka, 1978. – 512 s.

Bache, K. UCI Machine Learning Repository / K. Bache, M. Lichman. – Irvine, CA: University of California, School of Information and Computer Science, 2013. Url: http://archive.ics.uci.edu/ml.

Ho, Y.-C. An algorithm for linear inequalities and its applications / Y.-C. Ho, R. Kashyap // IEEE Trans. Elec.Comp. – 1965. – Vol. 14. – pp. 683–688.

Hassoun, M.H. Ho-Kashyap Rules for Perceptron Training / M.H. Hassoun, J.Song // IEEE Transactions on Neural Networks. – 1992 . – Vol. 3. – pp. 51–61.

Ho, Y.-C. A class of iterative procedures for linear inequalities / Y.-C. Ho, R. Kashyap // Journal of SIAM Control. – 1966. – Vol. 4. – pp. 112–115.

Lauer, F. Ho–Kashyap with early stopping vs soft-margin SVM for linear classifiers – an application / F. Lauer, M. Bentoumi, G. Bloch, G. Millґerioux // Advances in Neural Networks . – 2004. – Vol. 1. – pp. 524-530.

Leski, J. An ε–margin nonlinear classifier based on if–then rules / J. Leski // IEEE Transactions on Systems, Man and Cybernetics. – 2004 .–Vol. 34. – pp. 68-76.

Leski, J. Ho-Kashyap classifier with generalization control / J. Leski // Pattern Recognition Letters. – 2003. – Vol. 24. – pp. 2281-2290.

Trojanozhko, O.A. Optimizacija diagnostiki raka molochnoj zhelezy na osnove diskretnoj funkcii oshibok / O.A. Trojanozhko, I.D. Kolesin // Zhurnal "Izvestija Jugo-Zapadnogo gosudarstvennogo universiteta" Serija Upravlenie, vychislitel'naja tehnika, informatika. Medicinskoe priborostroenie. – 2016. – #3(20) – S. 125-132 (iz perechnja VAK, Url: https://www.swsu.ru/izvestiya/seriesivt/archiv/3_2016.pdf)

Trojanozhko, O.A. Vizualizacija processa optimizacii parametrov kriterial'noj funkcii oshibok v zadache medicinskoj diagnostiki / I.D. Kolesin, O.A. Trojanozhko, P.P. Sivashhenko // Nauchnaja vizualizacija. 2017. T. 9. S. 26-40. (iz BD SCOPUS, Url: http://sv-journal.org/2017-4/03.php?lang=ru).


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность MoNeTec 2024

ISSN: 2307-8162