RUS  ENG
Full version
JOURNALS // Computer Optics // Archive

Computer Optics, 2018 Volume 42, Issue 4, Pages 688–694 (Mi co550)

This article is cited in 4 papers

IMAGE PROCESSING, PATTERN RECOGNITION

Method of nephroscintigraphic dynamic images analysis

A. V. Gaidelab, A. V. Kapishnikovc, Yu. S. Pyshkinac, A. V. Kolsanovc, A. G. Khramova

a Samara National Research University, 443086, Russia, Samara, Moskovskoye shosse 34
b IPSI RAS – Branch of the FSRC “Crystallography and Photonics” RAS, 443001, Samara, Russia, Molodogvardeyskaya 151
c Samara State Medical University, Samara, Russia

Abstract: We propose a method for automatic processing of dynamic nephroscintigrams based on fitting the renogram curve by an exponential function. The method makes it possible to obtain objective parameters of the kidney condition. The performance of the method is studied on a set of radionuclide images of a transplant. Results of clinical studies confirming the diagnostic efficiency of the developed approach are presented. Analysis of the kinetics of the nephrotropic indicator provides an accurate assessment of the functional status of the transplanted kidney. Two numerical parameters are revealed that offer a higher diagnostic efficiency when calculated from the constructed model compared to when they are calculated from the original renogram.

Keywords: image processing, pattern recognition, scintigraphy, nephrology, transplantation.

Received: 09.04.2018
Accepted: 04.07.2018

DOI: 10.18287/2412-6179-2018-42-4-688-694



© Steklov Math. Inst. of RAS, 2024