A method for digital renal scintigram analysis based on brightness and geometric features

Автор: Gaidel Andrey Viktorovich, Khramov Alexander Grigorievich, Kapishnikov Aleksandr Viktorovich, Kolsanov Aleksandr Vladimirovich, Pyshkina Yuliya Sergeevna

Журнал: Компьютерная оптика @computer-optics

Рубрика: Обработка изображений: Распознавание образов

Статья в выпуске: 1 т.41, 2017 года.

Бесплатный доступ

We proposed a method of automated scintigram image processing enabling an objective evaluation of the renal parenchyma condition to be made based on scintigram brightness and geometric characteristics with threshold processing. We studied the method using a set of real radionuclide images of a renal transplant. The results of clinical studies confirm the effectiveness of the developed method. We obtained objective numerical values associated with thresholding the image from 40% to 80%, based on which one can form an independent assessment of the presence or absence of focal lesions in the renal parenchyma.

Image processing, pattern recognition, scintigraphy, kidney disease, transplantation

Короткий адрес: https://sciup.org/14059528

IDR: 14059528   |   DOI: 10.18287/2412-6179-2017-41-1-103-109

Статья научная