rentradВестник рентгенологии и радиологииJournal of radiology and nuclear medicine0042-46762619-0478Limited Liability Company "LUCHEVAYA DIAGNOSTIKA", Russian Association of Radiologists10.20862/0042-4676-2023-104-1-40-46rentrad-780Research ArticleОРИГИНАЛЬНЫЕ СТАТЬИORIGINAL RESEARCHВыявление жирового гепатоза с помощью компьютерного зрения при низкодозной компьютерной томографии органов грудной клетки в программе скрининга рака легкогоHepatic Steatosis Detection by Computer Vision During Chest Low-Dose Computed Tomography in Lung Cancer Screening Programhttps://orcid.org/0000-0002-0640-2874ЗахароваД. К.ZakharovaD. К.

Захарова Дарья Константиновна, студентка 

ул. Трубецкая, 8, стр. 2, Москва, 119435

Daria К. Zakharova, Student 

ul. Trubetskaya, 8, str. 2, Moscow, 119435

https://orcid.org/0000-0001-5994-0468НудновН. В.NudnovN. V.

Нуднов Николай Васильевич, д. м. н., профессор, зам. директора по научной работе, заведующий научно-исследовательским отделом комплексной диагностики заболеваний и радиотерапии 

ул. Профсоюзная, 86, Москва, 117997

Nikolay V. Nudnov, Dr. Med. Sc., Professor, Deputy Director for Science, Head of Research Department of Complex Diagnostics of Diseases and Radiotherapy 

ul. Profsoyuznaya, 86, Moscow, 117997

https://orcid.org/0000-0002-0166-3768КоденкоМ. Р.KodenkoМ. R.

Коденко Мария Романовна, мл. науч. сотр. отдела научных медицинских исследований 

ул. Петровка, 24, стр. 1, Москва, 127051

Мaria R. Kodenko, Junior Researcher, Department of Scientific Medical Research 

ul. Petrovka, 24, str. 1, Moscow, 127051

https://orcid.org/0000-0002-9661-0254РешетниковР. В.ReshetnikovR. V.

Решетников Роман Владимирович, к. ф.-м. н., начальник отдела научных медицинских исследований 

ул. Петровка, 24, стр. 1, Москва, 127051

Roman V. Reshetnikov, Cand. Phys-Math. Sc., Head of Department of Scientific Medical Research 

ul. Petrovka, 24, str. 1, Moscow, 127051

https://orcid.org/0000-0001-5161-6540ГончарА. П.GoncharА. P.

Гончар Анна Павловна, мл. науч. сотр. отдела научных медицинских исследований 

ул. Петровка, 24, стр. 1, Москва, 127051

Аnna P. Gonchar, Junior Researcher, Department of Scientific Medical Research 

ul. Petrovka, 24, str. 1, Moscow, 127051

anne.gonchar@gmail.comФГАОУ ВО «Первый Московский государственный медицинский университет им. И.М. Сеченова» Минздрава РоссииРоссияSechenov First Moscow State Medical University (Sechenov University)Russian FederationФГБУ «Российский научный центр рентгенорадиологии»РоссияRussian Scientific Center of RoentgenoradiologyRussian FederationГБУЗ «Научно-практический клинический центр диагностики и телемедицинских технологий» Департамента здравоохранения г. МосквыРоссияResearch and Practical Clinical Center for Diagnostics and Telemedicine TechnologiesRussian Federation20230106202310414046Copyright © Захарова Д.К., Нуднов Н.В., Коденко М.Р., Решетников Р.В., Гончар А.П., 20232023Захарова Д.К., Нуднов Н.В., Коденко М.Р., Решетников Р.В., Гончар А.П.Zakharova D.К., Nudnov N.V., Kodenko М.R., Reshetnikov R.V., Gonchar А.P.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.russianradiology.ru/jour/article/view/780

Актуальность. Низкодозная компьютерная томография (НДКТ) органов грудной клетки (ОГК) применяется для скрининга рака легкого, но данные исследования можно использовать и для оценки состояния печени, в т.ч. выявления жирового гепатоза (ЖГ). Однако врачи-рентгенологи часто не проводят оценку изменений печени из-за концентрации внимания на ОГК. Цель: определить выявляемость КТ-признаков ЖГ среди пациентов группы скрининга рака легкого с помощью системы компьютерного зрения (КЗ). Материал и методы. Для ретроспективного исследования было отобрано 300 НДКТ ОГК пациентов из группы проекта скрининга рака легкого г.Москвы в период 2018–2020 гг. Анализ КТ-плотности печени проводили с применением системы КЗ, КТ-признаками ЖГ считали значения плотности печени < 40 HU. Дополнительно выполнен анализ текстовых протоколов описания и заключений отобранных исследований. Проведено сравнение выявляемости КТ-признаков ЖГ врачами-рентгенологами и системой КЗ. Результаты. В анализ включены данные 291 пациента, медиана возраста для всей выборки составила 65 [61; 70] лет. Среднее значение КТ-плотности печени определено на уровне 55,6 ± 14,8 HU. Плотность печени < 40 HU зафиксирована у 13% больных (23 (16,1%) мужчины и 14 (9,5%) женщин). Выявлена статистически достоверная разница между показателями плотности печени у этих пациентов (р = 0,04). В группу риска наличия ЖГ (40–45 HU) вошли 6 (4,2%) мужчин и 4 (2,7%) женщины. При пересмотре текстовых протоколов описания исследований, в которых плотность печени составила < 40 HU, во всех случаях отмечено отсутствие указания на патологию. Заключение. Выявляемость КТ-признаков ЖГ среди пациентов группы скрининга рака легкого г. Москвы составила 13%. Отсутствие указаний на данную патологию в протоколах текстовых описаний подчеркивает актуальность применения систем КЗ в рутинной практике врача- рентгенолога.

Background. Chest low-dose computed tomography (LDCT) is used in lung cancer screening, but the study data can also be used to assess the liver condition, including the hepatic steatosis (HS) detection. However, radiologists often do not pay attention to liver changes due to the focus on the chest. Objective: to determine the prevalence of HS during chest LDST among lung cancer screening patients using a computer vision (CV) system. Material and methods. For a retrospective study, 300 chest LDCT were taken from Moscow lung cancer screening in 2018–2020. Hepatic attenuation analysis was performed by CV, the values < 40 HU were considered as HS. The text protocols of CT scans were analysed and compared with decreased hepatic attenuation revealed by CV system. Results. 291 patients were analysed, the median age for the sample was 65 [61; 70] years. The mean hepatic attenuation was 55.6 ± 14.8 HU. Hepatic attenuation < 40 HU was found in 13% patients (23 (16.1%) males and 14 (9.5%) females), a statistically significant difference was revealed among these patients (p = 0.04). Six (4.2%) males and 4 (2.7%) females were at risk for HS (40–45 HU). The examination of text protocols showed no pathology discovered in all cases. Conclusion. The prevalence of CT signs for HS among the lung cancer screening group in Moscow was 13%. The absence of HS in text protocols highlights the importance of using CV systems in the routine practice.

низкодозная компьютерная томографияжировой гепатозкомпьютерное зрениеоппортунистический скринингскрининг рака легкогоlow-dose computerized tomographyhepatic steatosiscomputer visionopportunistic screeninglung cancer screeningReferencesСтруков А.И., Серов В.В. Патологическая анатомия. М.: Литтерра; 1995: 491–4.Strukov AI, Serov VV. Pathological anatomy. Мoscow: Litterra; 1995: 491–4 (in Russ.).EASL-EASD-EASO Clinical Practice Guidelines for the management of non-alcoholic fatty liver disease. J Hepatol. 2016; 64(6): 1388–402. http://doi.org/10.1016/j.jhep.2015.11.004.EASL-EASD-EASO Clinical Practice Guidelines for the management of non-alcoholic fatty liver disease. J Hepatol. 2016; 64(6): 1388–402. http://doi.org/10.1016/j.jhep.2015.11.004.Armstrong MJ, Adams LA, Canbay A, Syn WK. Extrahepatic complications of nonalcoholic fatty liver disease. Hepatology. 2014; 3(59): 1174–97. http://doi.org/10.1002/hep.26717.Armstrong MJ, Adams LA, Canbay A, Syn WK. Extrahepatic complications of nonalcoholic fatty liver disease. Hepatology. 2014; 3(59): 1174–97. http://doi.org/10.1002/hep.26717.Mikolasevic I, Milic S, Turk Wensveen T, et al. Nonalcoholic fatty liver disease – a multisystem disease? World J Gastroenterol. 2016; 22(43): 9488–505. http://doi.org/10.3748/wjg.v22.i43.9488.Mikolasevic I, Milic S, Turk Wensveen T, et al. Nonalcoholic fatty liver disease – a multisystem disease? World J Gastroenterol. 2016; 22(43): 9488–505. http://doi.org/10.3748/wjg.v22.i43.9488.Del Ben M, Baratta F, Pastori D, Angelico F. The challenge of cardiovascular prevention in NAFLD. Lancet Gastroenterol Hepatol. 2021; 6(11): 877–8. http://doi.org/10.1016/S2468-1253(21)00337-X.Del Ben M, Baratta F, Pastori D, Angelico F. The challenge of cardiovascular prevention in NAFLD. Lancet Gastroenterol Hepatol. 2021; 6(11): 877–8. http://doi.org/10.1016/S2468-1253(21)00337-X.Kasper P, Lang S, Demir M, Steffen HM. Optimising the management of cardiovascular comorbidities in NAFLD patients: it’s time to (re-)act! Gut. 2022; 71(11): 2365–6. http://doi.org/10.1136/gutjnl-2021-326662.Kasper P, Lang S, Demir M, Steffen HM. Optimising the management of cardiovascular comorbidities in NAFLD patients: it’s time to (re-)act! Gut. 2022; 71(11): 2365–6. http://doi.org/10.1136/gutjnl-2021-326662.Bulut MD, Özdemir H, Bora A, et al. Comparison of computed tomography densitometry and shear wave elastography velocity measurements for evaluation of the liver volume in the nonalcoholic fatty liver disease. Int J Clin Exp Med. 2016; 6(9): 10159–69.Bulut MD, Özdemir H, Bora A, et al. Comparison of computed tomography densitometry and shear wave elastography velocity measurements for evaluation of the liver volume in the nonalcoholic fatty liver disease. Int J Clin Exp Med. 2016; 6(9): 10159–69.Graffy PM, Pickhardt PJ. Quantification of hepatic and visceral fat by CT and MR imaging: relevance to the obesity epidemic, metabolic syndrome and NAFLD. Br J Radiol. 2016; 89(1062): 20151024. http://doi.org/10.1259/bjr.20151024.Graffy PM, Pickhardt PJ. Quantification of hepatic and visceral fat by CT and MR imaging: relevance to the obesity epidemic, metabolic syndrome and NAFLD. Br J Radiol. 2016; 89(1062): 20151024. http://doi.org/10.1259/bjr.20151024.Блохин И.А., Лайпан А.Ш. Методические рекомендации по скринингу рака легкого. М.: Радиология Москвы; 2020: 60 с.Blokhin IA, Laypan AS. Methodological recommendations for lung cancer screening. Мoscow: Radiologia Moskvy; 2020: 60 pp. (in Russ.).Onuma Y, Tanabe K, Nakazawa G, et al. Noncardiac findings in cardiac imaging with multidetector computed tomography. J Am Coll Cardiol. 2006; 48(2): 402–6. http://doi.org/10.1016/j.jacc.2006.04.071.Onuma Y, Tanabe K, Nakazawa G, et al. Noncardiac findings in cardiac imaging with multidetector computed tomography. J Am Coll Cardiol. 2006; 48(2): 402–6. http://doi.org/10.1016/j.jacc.2006.04.071.Vierikko T, Järvenpää R, Autti T, et al. Chest CT screening of asbestos-exposed workers: lung lesions and incidental findings. Eur Respir J. 2007; 29(1): 78–84. http://doi.org/10.1183/09031936.00073606.Vierikko T, Järvenpää R, Autti T, et al. Chest CT screening of asbestos-exposed workers: lung lesions and incidental findings. Eur Respir J. 2007; 29(1): 78–84. http://doi.org/10.1183/09031936.00073606.Kullberg J, Hedström A, Brandberg J, et al. Automated analysis of liver fat, muscle and adipose tissue distribution from CT suitable for large-scale studies. Sci Rep. 2017; 7(1): 10425. http://doi.org/10.1038/s41598-017-08925-8.Kullberg J, Hedström A, Brandberg J, et al. Automated analysis of liver fat, muscle and adipose tissue distribution from CT suitable for large-scale studies. Sci Rep. 2017; 7(1): 10425. http://doi.org/10.1038/s41598-017-08925-8.Liao M, Zhao YQ, Liu XY, et al. Automatic liver segmentation from abdominal CT volumes using graph cuts and border marching. Comput Methods Programs Biomed. 2017; 143: 1–12. http://doi.org/10.1016/j.cmpb.2017.02.015.Liao M, Zhao YQ, Liu XY, et al. Automatic liver segmentation from abdominal CT volumes using graph cuts and border marching. Comput Methods Programs Biomed. 2017; 143: 1–12. http://doi.org/10.1016/j.cmpb.2017.02.015.Huang Q, Ding H, Wang X, Wang G. Fully automatic liver segmentation in CT images using modified graph cuts and feature detection. Comput Biol Med. 2018; 95: 198–208. http://doi.org/10.1016/j.compbiomed.2018.02.012.Huang Q, Ding H, Wang X, Wang G. Fully automatic liver segmentation in CT images using modified graph cuts and feature detection. Comput Biol Med. 2018; 95: 198–208. http://doi.org/10.1016/j.compbiomed.2018.02.012.Wu W, Zhou Z, Wu S, Zhang Y. Automatic liver segmentation on volumetric CT images using supervoxel-based graph cuts. Comput Math Methods Med. 2016; 2016: 9093721. http://doi.org/10.1038/s41598-018-28787-y.Wu W, Zhou Z, Wu S, Zhang Y. Automatic liver segmentation on volumetric CT images using supervoxel-based graph cuts. Comput Math Methods Med. 2016; 2016: 9093721. http://doi.org/10.1038/s41598-018-28787-y.Spinczyk D, Krasoń A. Automatic liver segmentation in computed tomography using general-purpose shape modeling methods. Biomed Eng Online. 2018; 17(1): 65. http://doi.org/10.1186/s12938-018-0504-6.Spinczyk D, Krasoń A. Automatic liver segmentation in computed tomography using general-purpose shape modeling methods. Biomed Eng Online. 2018; 17(1): 65. http://doi.org/10.1186/s12938-018-0504-6.Shin YJ, Chang W, Ye JC, et al. Low-dose abdominal CT using a deep learning-based denoising algorithm: a comparison with CT reconstructed with filtered back projection or iterative reconstruction algorithm. Korean J Radiol. 2020; 21(3): 356–64. http://doi.org/10.3348/kjr.2019.0413.Shin YJ, Chang W, Ye JC, et al. Low-dose abdominal CT using a deep learning-based denoising algorithm: a comparison with CT reconstructed with filtered back projection or iterative reconstruction algorithm. Korean J Radiol. 2020; 21(3): 356–64. http://doi.org/10.3348/kjr.2019.0413.Pickhardt PJ, Lubner MG, Kim DH, et al. Abdominal CT with model-based iterative reconstruction (MBIR): initial results of a prospective trial comparing ultralow-dose with standarddose imaging. AJR Am J Roentgenol. 2012; 99(6): 1266–74. http://doi.org/10.2214/AJR.12.9382.Pickhardt PJ, Lubner MG, Kim DH, et al. Abdominal CT with model-based iterative reconstruction (MBIR): initial results of a prospective trial comparing ultralow-dose with standarddose imaging. AJR Am J Roentgenol. 2012; 99(6): 1266–74. http://doi.org/10.2214/AJR.12.9382.Boyce CJ, Pickhardt PJ, Kim DH, et al. Hepatic steatosis (fatty liver disease) in asymptomatic adults identified by unenhanced low-dose CT. AJR Am J Roentgenol. 2010; 194(3): 623–8. http://doi.org/10.2214/AJR.09.2590.Boyce CJ, Pickhardt PJ, Kim DH, et al. Hepatic steatosis (fatty liver disease) in asymptomatic adults identified by unenhanced low-dose CT. AJR Am J Roentgenol. 2010; 194(3): 623–8. http://doi.org/10.2214/AJR.09.2590.van de Wiel JC, Wang Y, Xu DM, et al. Neglectable benefit of searching for incidental findings in the Dutch-Belgian lung cancer screening trial (NELSON) using low-dose multidetector CT. Eur Radiol. 2007; 17(6): 1474–82. http://doi.org/10.1007/s00330-006-0532-7.van de Wiel JC, Wang Y, Xu DM, et al. Neglectable benefit of searching for incidental findings in the Dutch-Belgian lung cancer screening trial (NELSON) using low-dose multidetector CT. Eur Radiol. 2007; 17(6): 1474–82. http://doi.org/10.1007/s00330-006-0532-7.Chen X, Ma T, Yip R, et al. Elevated prevalence of moderateto-severe hepatic steatosis in World Trade Center General Responder Cohort in a program of CT lung screening. Clin Imaging. 2020; 60(2): 237–43. http://doi.org/10.1016/j.clinimag.2019.12.009.Chen X, Ma T, Yip R, et al. Elevated prevalence of moderateto-severe hepatic steatosis in World Trade Center General Responder Cohort in a program of CT lung screening. Clin Imaging. 2020; 60(2): 237–43. http://doi.org/10.1016/j.clinimag.2019.12.009.Graffy PM, Sandfort V, Summers RM, Pickhardt PJ. Automated liver fat quantification at nonenhanced abdominal CT for population-based steatosis assessment. Radiology. 2019; 293(2): 334–42. http://doi.org/10.1148/radiol.2019190512.Graffy PM, Sandfort V, Summers RM, Pickhardt PJ. Automated liver fat quantification at nonenhanced abdominal CT for population-based steatosis assessment. Radiology. 2019; 293(2): 334–42. http://doi.org/10.1148/radiol.2019190512.Lawrence EM, Pooler BD, Pickhardt PJ. Opportunistic screening for hereditary hemochromatosis with unenhanced CT: determination of an optimal liver attenuation threshold. AJR Am J Roentgenol. 2018; 211(6): 1206–11. http://doi.org/10.2214/AJR.18.19690.Lawrence EM, Pooler BD, Pickhardt PJ. Opportunistic screening for hereditary hemochromatosis with unenhanced CT: determination of an optimal liver attenuation threshold. AJR Am J Roentgenol. 2018; 211(6): 1206–11. http://doi.org/10.2214/AJR.18.19690.

The authors declare that there are no conflicts of interest present.