Номер №4, 2018 - page 40-45

Fast in vivo assessmant of the urinary bladder connective tissue state for evaluation of the radiation injury severity

Strel'cova O.S., Moiseev A.A., Kiseleva E.B., Maslennikova A.B., Tararova E.A.
Information about authors:
  • Streltsova O.S. – Dr.Sc., Professor, Department of Urology named after E.V. Shahov of Privolzhsky Research Medical University of the Ministry of Health of Russia; e-mail: strelzova_uro@ mail.ru
  • Moiseev A.A. – PhD, Senior Researcher, Institute of Applied Physics, RAS
  • Kiseleva E.B. – PhD., Researcher of the Laboratory of Optical Coherence Tomography of the Research Institute of Experimental Oncology and Biomedical Technologies, Privolzhsky Research Medical University of the Ministry of Health of Russia
  • Maslennikova A.V. – Dr.Sc., professor of the department of oncology, radiation therapy, radiation diagnostics of Privolzhsky Research Medical University of the Ministry of Health of Russia;Professor of the Department of Biophysics
  • Tararova E.A. – PhD, oncologist of the Nizhny Novgorod Regional Clinical Oncological Dispensary

In this work we proposed an algorithm for “operator-independent” quantitative assessment of the bladder images under various pathological conditions obtained by the cross-polarization optical coherence tomography (CP OCT).

The aim of ourstudywasto develop a method for operative diagnostics of the bladder connective tissue matrix state based onCP OCT data,which would allow calculating with certain accuracy the probability of development of the severe complications during radiation therapy of the pelvic organs diseases."OKT-1300U" equipmentwas used. 4 groups ofCP OCT sets of bladderimages were analyzed for numerical analysis and fortheir automatic classification: contingent standards (n = 22), chronic cystitis with predominance of epithelial atrophy and fibrosisin the mucosa and submucosa structures (n = 122), I-II (n = 40) and III-IV (n = 34) degrees of radiation injury. An algorithm based on the analysis of principal component and a Random Forest Tree classification algorithm were applied for automatic identification of pathological changes in CP OCT images. A predictive model, which allowed distinguishing not only CP OCT images of normal bladdertissue from chronic cystitis but also different clinical groups of radiation injury, was developed using the analysis of the error curve.

The independent from the investigator’s qualifications method, which allowsto promptly evaluate the probability of bladdersevere complications during radiation therapy treatment planning and to verify irreversible changes in the bladder (III-IV clinical degree of complications) from reversible changes (I - II clinical degree of complications) in the period aer irradiation, was developed.

Authors declare lack of the possible conflicts of interests

Download544.96 KB
radiation cystitis, connective tissue matrix of the bladder, cross-polarization optical coherence tomography, numerical analysis, automatic classification of images

Readera - Социальная платформа публикаций

Crossref makes research outputs easy to find, cite, link, and assess