CLINICAL AND RADIOLOGICAL PARALLELS IN THE DIAGNOSIS OF PRIMARY LUNG CANCER USING MATHEMATICAL MODELING TECHNOLOGIES

Author:

Borisenko Olga V.12ORCID,Lazarev Alexander F.

Affiliation:

1. Regional state medical institution "Altai Regional Oncology Dispensary"

2. Federal State Budgetary Educational Institution of Higher Education "Altai State Medical University" of the Ministry of Health of the Russian Federation

Abstract

The problem of lung cancer (LC) is becoming increasingly relevant every year. According to the cancer registry of the Altai Regional Oncology Center, the incidence of lung cancer in 2019 was 114.8 per 100 thousand population for men, 19.3 per 100 thousand population for women; in 2020 – 96.8 and 16.8, respectively. In 2021, the incidence was 108.9 per 100 thousand population. Diagnostic rates in 2022 among patients with respiratory cancer were disappointing, since at the time of diagnosis 42.2% had stage IV of the disease, 27.9% had stage III, 16.3% had stage I and 12.9% had stage II. and in 0.7% of cases the stage was not established. When analyzing the distribution of LC patients of different age groups depending on the tumor histotype, it was found that the majority are adenocarcinoma and squamous cell LC – 85%. Our study used MSCT data from 485 patients with LC aged from 45 to 80 years. Digital analysis of the scans was carried out using the “Radiologist+” program (Russia, Barnaul), which allows direct sampling of average pixel densities in tabular form in selected areas of interest from files in DICOM format for subsequent analysis and statistical processing. The resulting densitometric indicators were fed to the inputs of the artificial neural network. The effectiveness of differential diagnosis of histological forms, taking into account the presence or absence of tobacco smoking in patients: sensitivity 85.8%, specificity 85.0%, accuracy 85.4%.

Publisher

ECO-Vector LLC

Reference7 articles.

1. Grigoruk O.G., Tsoi D.A., Bazulina L.M., Vikhlyanov I.V. Small cell lung cancer. Cytological diagnosis. Malignant tumors. 2022; 12 (1): 36–43

2. Kosenok, V.K. Statistical patterns of lung cancer incidence in the Omsk region. /VC. Kosenok, L.V. Belskaya, J. Massard and others // Siberian Journal of Oncology. –2016.– No. 15 (4).– P. 21– 25.

3. Kosterina N.E., Grinberg L.M. Cytological research methods in the complex morphological diagnosis of small cell lung cancer based on materials from “small samples”. PATHOMORPHOLOGY No. 10 (178) September 2019.

4. Merabishvili, V.M. Medium-term variant forecast of mortality of the Russian population from malignant neoplasms / V.M. Merabishvili // Siberian Journal of Oncology. –2019.– No. 18 (4).– 5–12.

5. Trotsenko, S.D. Modern problems of postoperative radiation therapy for non-small cell lung cancer / S.D. Trotsenko, V.M. Sotnikov, G.A. Panshin et al. // Bulletin of radiology and radiology. – 2015. – No. 2. – P. 47 – 57.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3