Possibilities of differential diagnostics of histologicalforms of primary lung cancer with multi-spiral computed tomography based on artificial intelligence

Abstract

The problem of lung cancer, visualized including spherical formation of the lung, is becoming increasingly important every year. In the structure of the oncological morbidity of the Russian population among men in 2018, this pathology occupied the leading position – 16.9% (in women – 4.0%). When analyzing the distribution of patients with lung cancer of various age groups depending on the histotype of the tumor, it was found that in most cases it is adenocarcinoma and squamous lung cancer – 85%. MSCT was performed in 342 patients with spherical formation of the lung aged 45 to 80 years using computed tomographs Aquillion 64 and Asteion 4 (Toshiba Medical Systems). Digital analysis of scans was performed using the X-ray + program (Russia, Barnaul), which allows direct sampling of average pixel densities in a tabular form in selected areas of interest from DICOM files for subsequent analysis and statistical processing. The obtained densitometric indicators were received at the inputs of an artificial neural network. The effectiveness of differential diagnosis of histological forms: sensitivity – 35.7 + 2.6%, specificity – 40.6 + 2.6%, accuracy –76.3 + 2.3%.

Keywords

computed tomography / histological forms of lung cancer / artificial intelligence

References

[1] Grigoryevskaya Z. V., Utkina V. L., Byakhova V. A. et al. Difficulties in the differential diagnosis of lung cancer and inflammatory changes in lung tissue. Siberian Oncology Journal. 2018; 17 (5): 119–24.

[2] Григорьевская З.В., Уткина В.Л., Бяхова В.А. и др. Трудности дифференциальной диагностики рака лёгкого и воспалительных изменений легочной ткани. Сибирский онкологический журнал. 2018; 17 (5): 119–24.

[3] Jemal A., Vines P., Bray F. et al. Atlas of modern oncology. Second Edition. Atlanta, Georgia: American Cancer Society. 2014. Access Mode: http://www.cancer.org/canceratlas.

[4] Джемал А., Винес П., Брей Ф. и др. Атлас современной онкологии. Издание второе. Атланта, Джорджия: Американское онкологическое общество. 2014. Режим доступа: http://www.cancer.org/canceratlas.

[5] Kaprin A.D., Starinsky V.V., Petrova G.V., ed. Malignant neoplasms in Russia in 2018 (morbidity and mortality). M.: FGBU MNIII im. P.A. Herzen. 2019.250 p.

[6] Каприн А.Д., Старинский В.В., Петрова Г.В., ред. Злокачественные новообразования в России в 2018 году (заболеваемость и смертность). М.: ФГБУ МНИОИ им. П.А. Герцена. 2019. 250 с.

[7] Korolyuk I.P. Evidence-based radiology: basic principles and approaches to its implementation. Radiology-practice. 2007; 5: 7–21.

[8] Королюк И.П. Доказательная радиология: основные принципы и подходы к ее реализации. Радиология-практика. 2007; 5: 7–21.

[9] Kosenok V.K., Belskaya L.V., Massard J. et al. Statistical patterns of the incidence of lung cancer in the Omsk region. Siberian Oncology Journal. 2016; 15 (4): 21–5.

[10] Косенок В.К., Бельская Л.В., Массард Ж. и др. Статистические закономерности заболеваемости раком лёгкого в Омской области. Сибирский онкологический журнал. 2016; 15 (4): 21–5.

[11] Merabishvili V.M. Medium-term variant forecast of mortality of the population of Russia from malignant neoplasms. Siberian Oncology Journal. 2019; 18 (4): 5–12.

[12] Мерабишвили В.М. Среднесрочный вариантный прогноз смертности населения России от злокачественных новообразований. Сибирский онкологический журнал. 2019; 18 (4): 5–12.

[13] Merabishvili V.M., Arsenyev A.I., Tarkov S.A. et al. Morbidity and mortality from lung cancer, reliability of accounting. Siberian Oncology Journal. 2018; 17 (6): 15–26.

[14] Мерабишвили В.М., Арсеньев А.И., Тарков С.А. и др. Заболеваемость и смертность населения от рака лёгкого, достоверность учета. Сибирский онкологический журнал. 2018; 17 (6): 15–26.

[15] Petrova G.V., Gretsova O.P., Starinsky V.V. Comparison of data from state oncological statistics and cancer register of Russia. Siberian Oncology Journal. 2019; 18 (5): 5–11.

[16] Петрова Г.В., Грецова О.П., Старинский В.В. Сравнение данных государственной онкологической статистики и ракового регистра России. Сибирский онкологический журнал. 2019; 18 (5): 5–11.

[17] Recommendations for the early diagnosis of lung cancer for primary care physicians. Editorial. Bulletin of radiology and radiology. 2016; 97 (2): 69–78.

[18] Рекомендации по ранней диагностике рака лёгкого для врачей первичного звена. Редакционная статья. Вестник рентгенологии и радиологии. 2016; 97 (2): 69–78.

[19] Choynzonov E.L., Zhuikova L.D., Odintsova I.N. Mortality of the population of the Tomsk region from malignant neoplasms of the respiratory system. Siberian Oncology Journal. 2018; 17 (3): 5–10.

[20] Чойнзонов Е.Л., Жуйкова Л.Д., Одинцова И.Н. Смертность населения Томской области от злокачественных новообразований дыхательной системы. Сибирский онкологический журнал. 2018; 17 (3): 5–10.

[21] Guldbrandt L. M., Fenger-Grøn M., Rasmussen T. R. et al. The effect of direct access to CT scan in early lung cancer detection: an unblinded, cluster-randomised trial. BMC Cancer. 2015; 15: 934.

RIGHTS & PERMISSIONS

Eco-Vector