М.К. MIKHAILOV¹, Е.А. ROMANYCHEVA², V.V. SEVASTYANOV³, Ya.А. FURMAN³

¹Kazan State Medical Academy — Branch Campus of the RMACPE MOH Russia, 36 Butlerov Str., Kazan, Russian Federation, 420012

²Republic Oncology Dispensary, 22 Osipenko Str., Yoshkar-Ola, Russian Federation, 424037

³Volga State University of Technology, 3 Lenin square, Yoshkar-Ola, Russian Federation, 424000

Mikhailov M.K. — D. Med. Sc., Professor, Head of the Department of Radiodiagnostics, tel. (8432) 36-95-83, e-mail: mikhailovmk@mail.ru.

Romanycheva E.A. — radiologist, tel. +7-927-884-76-50, e-mail: katerina.rrr@bk.ru.

Sevastyanov V.V. — D. Med. Sc., Professor of the Department of Radiotechnical and Medical-Biological Systems, tel. (8362) 64-46-58, e-mail: cpr@mari-el.ru

Furman Ya.A. — D. Eng. Sc., Professor of the Department of Radiotechnical and Medical-Biological Systems, tel. (8362) 68-78-05, e-mail: FurmanYA@volgatech.net

 X-ray mammography is considered one of the primary diagnostic methods for malignant breast tumors. Since the conclusion is mainly based on the visual analysis of analog or digital X-ray images of the breast, the objectivity of the method is highly dependent on the professional experience of the radiologist. Therefore, the automation of the process of analyzing X-ray mammograms is a relevant task. The present research objective is to develop a method for automatic classification of the types of tumors on x-ray mammograms. To this end, the boundaries of breast tissue densities were described analytically using the mathematical apparatus of contour analysis. It has been found that malignant tumors are characterized by indented contours. This enables to determine the tumor type by calculating the straightness coefficient of its contour. The straightness coefficient values for malignant and benign tumors have been found. Based on a representative sample from the patients with a previously known diagnosis, consistent classification results have been obtained which indicates the feasibility of the proposed method.

Key words: X-ray mammography; malignant breast tumors; criteria of malignancy; mathematical methods of contour analysis; quantitative analysis.

REFERENCES

1. Rozhkova N.I., Burdina I.I., Dabagov A.R., Mazo M.L., Prokopenko S.P., Yakobs O.E. Luchevaya diagnostika v mammologii: rukovodstvo dlya vrachey [Radiodiagnosis in mammology: a guide for doctors]. Moscow: SIMK, 2014.
2. Romanycheva E.A., Ivanov K.O., Batukhtin D.M., Sevast’yanov V.V., Furman Ya.A., Eruslanov R.V. Programma dlya kolichestvennoy otsenki formy konturov ob»ektov mammograficheskogo izobrazheniya, versiya 1.0. Svidetel’stvo o gosudarstvennoy registratsii programmy dlya EVM no. 2015612821 ot 26.02.2015 [A program for quantifying the shape of contours of mammographic image objects, version 1.0. Certificate of state registration of the computer program № 2015612821 of 26.02.2015].
3. Romanycheva E.A., Ivanov K.O., Batukhtin D.M., Sevast’yanov V.V., Furman Ya.A., Eruslanov R.V. Programma dlya segmentatsii ob»ektov mammograficheskogo rentgenovskogo izobrazheniya s minimal’nym iskazheniem ikh formy, versiya 1.0. Svidetel’stvo o gosudarstvennoy registratsii programmy dlya EVM no. 2015612897 ot 26.02.2015 [Program for segmentation of mammographic X-ray image objects with minimal distortion of their shape, version 1.0. Certificate of state registration of the computer program № 2015612897 of 26.02.2015].
4. Furman Ya.A., Krevetskiy A.V., Peredreev A.K. Vvedenie v konturnyy analiz i ego prilozheniya k obrabotke izobrazheniy i signalov. 2-e izd., ispr. [Introduction to contour analysis and its applications to the processing of images and signals. 2 nd ed., rev.]. Moscow: FIZMATLIT, 2003.
5. Romanycheva E.A., Batukhtin D.M., Ivanov K.O., Sevast’yanov V.V., Furman Ya.A., Eruslanov R.V. Classification of objects by their form on mammographic images using contour analysis methods. Vestnik Povolzhskogo gosudarstvennogo tekhnologicheskogo universiteta, seriya “Radiotekhnicheskie i infokommunikatsionnye sistemy”, 2014;4(23): 58-71 (in Russ.).
6. Mikhaylov M.K., Sevast’yanov V.V., Furman Ya.A., Romanycheva E.A. Differentsial’naya diagnostika izobrazheniy novoobrazovaniy s sil’noy variabel’nost’yu formy na rentgenologicheskikh mammogrammakh metodami konturnogo analiza: Materialy IX Vserossiyskogo natsional’nogo kongressa luchevykh diagnostov i terapevtov “RADIOLOGIYa-2015” [Differential diagnosis of images of tumors with a strong shape variability on X-ray mammograms by the methods of contour analysis: Proceedings of the 9th All-Russian National Congress of Radiation Diagnostics and Therapeutists «RADIOLOGY-2015»]. Moscow, 2015; 5(2): 112.
7. Batukhtin D.M., Romanycheva E.A., Sevast’yanov V.V., Ivanov K.O., Furman Ya.A. Combined methods of classification of objects on mammographic images. Nauchno-tekhnicheskiy zhurnal “Meditsinskaya tekhnika”. 2016;2(296): 19-22 (in Russ.).
8. Mikhaylov M.K., Romanycheva E.A., Sevast’yanov V.V., Furman Ya.A. Metod konturnogo analiza novoobrazovaniy na rentgenovskikh mammogrammakh: Materialy Yubileynogo Kongressa Rossiyskogo obshchestva rentgenologov i radiologov [Method of contour analysis of neoplasms on X-ray mammograms: Materials of the Jubilee Congress of the Russian Society of Radiologists and Radiologists]. Moscow, 2016: 141.
9. Romanycheva E.A., Sevastyanov V.V., Furman Ya.A. Method of contour analysis of neoplasms in X-ray mammograms: Proceedings of the European Congress of Radiology (ECR 2016), 2016, March 2-6; Vienna; Austria, available at: http://posterng.netkey.at/esr/viewing/index.php?module=viewing_poster&doi=10.1594/ecr2016/C-0073
10. Baker J.A., Rosen E.L., Lo J.Y., Gimenez E.I., Walsh R., Soo M.S. Computer-Aided Detection (CAD) in screening mammography: sensitivity of commercial CAD systems for detecting architectural distortion. Am. J. Roentgenol., 2003; 181: 1083-1088. DOI: 10.2214/ajr.181.4.1811083.
11. Dheeba J., Albert Singh N., Tamil Selvi S. Computer-aided detection of breast cancer on mammograms: A swarm intelligence optimized wavelet neural network approach. J. Biomed. Inform., 2014; 49: 45–52.
12. Lehman C.D., Wellman R.D., Buist D.S., Kerlikowske K., Tosteson A.N., Miglioretti D.L. Diagnostic accuracy of digital screening mammography with and without computer-aided detection. JAMA Intern. Med., 2015; 175 (11): 1828-1837. DOI: 10.1001/jamainternmed. 2015.5231.
13. Calas M.G.B., Gutfilen B. Pereira W.C.A. CAD and mammography: why use this tool? Radiol. Bras., 2012; 45 (1): 25–29.
14. Rozhkova N.I. X-ray radiological technologies in diagnostics of oncological diseases. Poliklinika. Luchevaya diagnostika. Spetsvypusk, 2014; 3: 20–22 (in Russ.).
15. Rozhkova N.I. Radial methods of examination of mammary glands. Poliklinika. Luchevaya diagnostika. Spetsvypusk, 2013; 3: 28–30 (in Russ.).
16. Rozhkova N.I., Gorshkov V.A., Kireeva M.N. et al. Tsifrovaya mammologicheskaya klinika. Tekhnologii vizualizatsii [Digital mammological clinic. Visualization technologies]. Moscow: SIMK, 2012.
17. Rozhkova N.I., Prokopenko S.P. Rentgenologicheskaya vizualizatsiya molochnoy zhelezy [X-ray visualization of the mammary gland]. Nauchno-tekhnicheskiy progress i radiologiya. Astana, Kazakhstan, 19–20 September. Materialy foruma, 1:159–169.
18. Tamkovich S.N., Voytsitskiy V.E., Laktionov P.P. Modern methods of diagnosing breast cancer. Biomeditsinskaya khimiya, 2014, 60 (2), pp. 141–160 (in Russ.).
19. Shakh B.A., Fundaro D.M., Mandava S. Luchevaya diagnostika zabolevaniy molochnoy zhelezy [Radiation diagnosis of breast diseases]. Moscow: BINOM. Laboratoriya znaniy, 2014.