Radiotekhnika
Publishing house Radiotekhnika

"Publishing house Radiotekhnika":
scientific and technical literature.
Books and journals of publishing houses: IPRZHR, RS-PRESS, SCIENCE-PRESS


Тел.: +7 (495) 625-9241

 

The osteoporosis diagnostics by the voting method on the texture feateres of x-ray images of femoral neck

Keywords:

V.R. Krasheninnikov – Dr. Sc. (Eng.), Professor, Head of Department «Applied Mathematics and Informatics», Ulyanovsk State Technical University
E-mail: kvrulstu@mail.ru
O.E. Malenova – Post-graduate Student, Department «Applied Mathematics and Informatics»,
Ulyanovsk State Technical University
E-mail: nika-lilu@yandex.ru


Early medical diagnosis largely determines the success of preventive and therapeutic measures. Osteoporosis is a very common disease of the skeletal system, which decreases bone strength. It is often diagnosed after bone fractures, so early diagnosis is of great importance. This disease has no pronounced symptoms, so often the diagnosis is made after fractures. For diagnostics, devices mea-suring bone mineral density are used, however, there are few such devices, therefore alternative diagnostic methods are suggested. One of them is the recognition of osteoporosis on X-rays images. The basic idea is as follows. A set of the image texture characteristics is selected and some classifier is constructed, which assigns the object in the image to the class of healthy or sick ones according to the values of these characteristics. The linear classifier is most often used. In this paper we investigate the osteoporosis diagnostic using four texture characteristics of X-ray femoral neck images (anisotropy, variation, Laplacian and the size of regions of constant brightness) and various variants of the voting classifier.

References:
  1. Gajdel' A.V., Pervushkin S.S. Issledovanie teksturny'x priznakov dlya diagnostiki zabolevanij kostnoj tkani po rentgenovskim izobrazheniyam // Komp'yuternaya optika. 2013. T. 37. № 1. S. 113−119.
  2. Vizil'ter Yu.V., Zheltov S.Yu., Bondarenko A.V., Osokov M.V. Obrabotka i analiz izobrazhenij. M.: Fizmatlit. 2010. 672 s.
  3. Krasheninnikov V.R., Bojczov A.A., Karusev D.N. Informativnost' nekotory'x xarakteristik dlya diagnostiki osteoporoza po rentgenogrammam // Radiotexnika. 2016. № 9. S. 32−35.
  4. Gajdel' A.V., Krasheninnikov V.R. Otbor priznakov dlya zadachi diagnostiki osteoporoza po rentgenovskim izobrazheniyam shejki bedra // Komp'yuternaya optika. 2016. № 6. S. 939−946.
  5. Krasheninnikov V.R., Kopylova A.S. Identification of pectinate structures in images of blood serum facia // Pattern recognition and image analysis. 2011. V. 21. № 3. P. 508−510.
  6. Krasheninnikov V.R., Potapov M.A. Estimation of parameters of geometric transformation of images by fixed-point method // Pattern recognition and image analysis. 2012. V. 22. № 2. P. 303−317.
  7. Nazmutdinova A.I., Milich V.N. Issledovanie zavisimosti rezul'tatov klassifikaczii mnogozonal'ny'x izobrazhenij lesnoj rastitel'nosti ot parametrov vejvlet-preobrazovaniya // Avtometriya. 2016. № 3. S. 20−27.

© Издательство «РАДИОТЕХНИКА», 2004-2017            Тел.: (495) 625-9241                   Designed by [SWAP]Studio