rentradВестник рентгенологии и радиологииJournal of radiology and nuclear medicine0042-46762619-0478Limited Liability Company "LUCHEVAYA DIAGNOSTIKA", Russian Association of Radiologists10.20862/0042-4676-2022-103-4-6-28-35rentrad-738Research ArticleОРИГИНАЛЬНЫЕ СТАТЬИORIGINAL RESEARCHТекстурный анализ КТ-изображений в дифференциации опухолей головы и шеиTexture Analysis of CT Images in Head and Neck Tumors Differentiationhttps://orcid.org/0000-0002-0058-5905ХоджибековаЮ. М.KhodjibekovaYu. M.

Ходжибекова Юлдуз М., д.м.н., профессор кафедры онкологии и медицинской радиологии

ул. Тараккиёт, 103, Ташкент, 100047

Yulduz M. Khodjibekova, Dr. Med. Sc., Professor, Chair of Oncology and Medical Radiology

ul. Taraqqiyot, 103, Tashkent, 100047

yulduz.khodjibekova@mail.ruhttps://orcid.org/0000-0002-4202-1913ХоджибековМ. Х.KhodjibekovM. Kh.

Ходжибеков Марат Х., д.м.н., профессор кафедры медицинской радиологии

ул. Фаробий, 2, Ташкент, 100109

Marat Kh. Khodjibekov, Dr. Med. Sc., Professor, Chair of Medical Radiology

ul. Farobiy, 2, Tashkent, 100109

https://orcid.org/0000-0003-1482-3510АхмедовБ. Р.AkhmedovB. R.

Ахмедов Бахтияр Р., к.м.н., ассистент кафедры медицинской радиологии

ул. Фаробий, 2, Ташкент, 100109

Bakhtiyor R. Akhmedov, MD, PhD, Assistant Professor, Chair of Medical Radiology

ul. Farobiy, 2, Tashkent, 100109

https://orcid.org/0000-0001-6570-9772ПаттоховА. Ш.PattokhovA. Sh.

Паттохов Азиз Ш., магистрант кафедры медицинской радиологии

ул. Фаробий, 2, Ташкент, 100109

Aziz Sh. Pattokhov, Master’s Student, Chair of Medical Radiology

ul. Farobiy, 2, Tashkent, 100109

https://orcid.org/0000-0001-8305-2313НигматжановА. С.NigmatdjanovA. S.

Нигматжанов Абдурашид С., ассистент кафедры медицинской радиологии

ул. Фаробий, 2, Ташкент, 100109

Abdurashid S. Nigmatdjanov, MD, Assistant Professor, Chair of Medical Radiology

ul. Farobiy, 2, Tashkent, 100109

Ташкентский государственный стоматологический институтУзбекистанTashkent State Dental InstituteUzbekistanТашкентская медицинская академияУзбекистанTashkent Medical AcademyUzbekistan2022261020221034-62835Copyright © Ходжибекова Ю.М., Ходжибеков М.Х., Ахмедов Б.Р., Паттохов А.Ш., Нигматжанов А.С., 20222022Ходжибекова Ю.М., Ходжибеков М.Х., Ахмедов Б.Р., Паттохов А.Ш., Нигматжанов А.С.Khodjibekova Y.M., Khodjibekov M.K., Akhmedov B.R., Pattokhov A.S., Nigmatdjanov A.S.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/738

Цель: определить диагностическую значимость текстурного анализа компьютерно-томографических изображений (КТТА) в дифференциации опухолей головы и шеи.Материал и методы. В исследование включены 118 пациентов в возрасте от 4 до 80 лет с верифицированным диагнозом доброкачественной и злокачественной опухоли (37 и 81 человек соответственно) головы и шеи. КТТА проводили с использованием программы LIFEx версии 6.30. Извлеченные из рутинных КТ-изображений 38 текстурных показателей подвергнуты регрессионному анализу с созданием логистических текстурных моделей с ассоциациями из четырех показателей в виде независимых предикторов.Результаты. Установлена возможность использования производных моделей – текстурных индексов вероятности для дифференциации доброкачественных и злокачественных опухолей: площадь под ROC-кривой (AUC) 0,854 ± 0,035 (p < 0,001); для разграничения местно-распространенных опухолей от местно-ограниченных: AUC 0,840 ± 0,049 (p < 0,001); для дискриминации умеренно-, низко-, и недифференцированного рака (G2, G3, G4) от высокодифференцированного (G1) рака головы и шеи: AUC 0,826 ± 0,085 (p < 0,001).Заключение. Текстурный анализ КТ-изображений позволяет неинвазивно предсказать доброкачественную или злокачественную природу визуализируемого образования головы и шеи, а также определить распространенность и степень злокачественности опухолевого поражения.

Objective: to determine the diagnostic significance of computed tomography texture analysis (CTTA) in differentiating head and neck tumors.Material and methods. The study included 118 patients aged from 4 to 80 years with a verified diagnosis of benign and malignant (37 and 81, respectively) head and neck tumors. CTTA was performed using the LIFEx program, version 6.30. Thirty eight (38) texture indices extracted from routine CT images were tested by regression analysis with creation of logistic texture models with associations of four indices as independent predictors.Results. The possibility of using derived models – probability textural indices for benign and malignant tumors differentiation was established: area under ROC-curve (AUC) 0.854 ± 0.035 (p < 0.001); for differentiation of locally spread from locally limited tumors: AUC 0.840 ± 0.049 (p < 0.001); for differentiation of moderately, poorly, and undifferentiated cancer (G2, G3, G4) from well-differentiated (G1) head and neck cancer: AUC 0.826 ± 0.085 (p < 0.001).Conclusion. CT images texture analysis allows to make non-invasive prognosis of benign or malignant nature of a visualized head and neck tumor, as well as to determine the extent and degree of tumor malignancy.

пространственная гетерогенностьтекстурный анализкомпьютерная томографияопухоли головы и шеиspatial heterogenicitytexture analysiscomputed tomographyhead and neck tumorsReferencesPetralia G, Bonello L, Viotti S, et al. CT perfusion in oncology: how to do it. Cancer Imaging. 2010; 10(1): 8–19. https://doi.org/10.1102/1470-7330.2010.0001.Petralia G, Bonello L, Viotti S, et al. CT perfusion in oncology: how to do it. Cancer Imaging. 2010; 10(1): 8–19. https://doi.org/10.1102/1470-7330.2010.0001.Силантьева Н.К., Петросян А.П., Агабабян Т.А., Шавладзе З.Н. Динамическая и перфузионная компьютерная томография при одиночных очагах в легких. Онкология. Журнал им. П.А. Герцена. 2017; 6(6): 55–61. https://doi.org/10.17116/onkolog20176655-61.Silantieva NK, Petrosian AP, Agababian TA, Shavladze ZN. Dynamic and perfusion computed tomography for solitary lung foci. P.A. Herzen Journal of Oncology. 2017; 6(6): 55–61 (in Russ). https://doi.org/10.17116/onkolog20176655-61.Masume N, Maryam M, Kayvan A, et al. Perfusion computed tomography scan imaging in differentiation of benign from malignant parotid lesions. Int Arch Otorhinolaryngol. 2020; 24(2): e160–9. https://doi.org/10.1055/s-0039-1697005.Masume N, Maryam M, Kayvan A, et al. Perfusion computed tomography scan imaging in differentiation of benign from malignant parotid lesions. Int Arch Otorhinolaryngol. 2020; 24(2): e160–9. https://doi.org/10.1055/s-0039-1697005.Lubner MG, Smith AD, Sandrasegaran K, et al. CT texture analysis: definitions, applications, biologic correlates, and challenges. Radiographics. 2017; 37(5): 1483–503. https://doi.org/10.1148/rg.2017170056.Lubner MG, Smith AD, Sandrasegaran K, et al. CT texture analysis: definitions, applications, biologic correlates, and challenges. Radiographics. 2017; 37(5): 1483–503. https://doi.org/10.1148/rg.2017170056.Чехун В.Ф., Шербан С.Д., Савцова З.Д. Гетерогенность опухоли – динамичное состояние. Онкология. 2012; 14(1): 4–12.Chekhun VF, Sherban SD, Savtsova ZD. Tumor heterogeneity – a dynamic state. Oncology. 2012; 14(1): 4–12 (in Russ).Геращенко Т.С., Денисов Е.В., Литвяков Н.В. и др. Внутриопухолевая гетерогенность: природа и биологическое значение. Биохимия. 2013; 78(11): 1531–49.Gerashchenko TS, Denisov EV, Litviakov NV, et al. Intratumor heterogeneity: nature and biological significance. Biokhimiya. 2013; 78(11): 1531–49 (in Russ).Lin G, Keshari KR, Park JM. Cancer metabolism and tumor heterogeneity: imaging perspectives using MR imaging and spectroscopy. Contrast Media Mol Imaging. 2017; 2017: 6053879. https://doi.org/10.1155/2017/6053879.Lin G, Keshari KR, Park JM. Cancer metabolism and tumor heterogeneity: imaging perspectives using MR imaging and spectroscopy. Contrast Media Mol Imaging. 2017; 2017: 6053879. https://doi.org/10.1155/2017/6053879.Nioche C, Orlhac F, Boughdad S, et al. LIFEx: a freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterization of tumor heterogeneity. Cancer Res. 2018; 78(16): 4786–9. https://doi.org/10.1158/0008-5472.CAN-18-0125.Nioche C, Orlhac F, Boughdad S, et al. LIFEx: a freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterization of tumor heterogeneity. Cancer Res. 2018; 78(16): 4786–9. https://doi.org/10.1158/0008-5472.CAN-18-0125.Nailon WH. Texture analysis methods for medical image characterisation. In: Mao Y (Ed). Biomedical imaging. London: IntechOpen; 2010. https://doi.org/10.5772/8912.Nailon WH. Texture analysis methods for medical image characterisation. In: Mao Y (Ed). Biomedical imaging. London: IntechOpen; 2010. https://doi.org/10.5772/8912.Romeo V, Cuocolo R, Ricciardi C, et al. Prediction of tumor grade and nodal status in oropharyngeal and oral cavity squamouscell carcinoma using a radiomic approach. Anticancer Res. 2020; 40: 271–80. https://doi.org/10.21873/anticanres.13949.Romeo V, Cuocolo R, Ricciardi C, et al. Prediction of tumor grade and nodal status in oropharyngeal and oral cavity squamouscell carcinoma using a radiomic approach. Anticancer Res. 2020; 40: 271–80. https://doi.org/10.21873/anticanres.13949.Bogowicz M, Riesterer O, Ikenberg K, et al. Computed tomography radiomics predicts HPV status and local tumor control after definitive radiochemotherapy in head and neck squamous cell carcinoma. Int J Radiat Oncol Biol Phys. 2017; 99(4): 921–8. https://doi.org/10.1016/j.ijrobp.2017.06.002.Bogowicz M, Riesterer O, Ikenberg K, et al. Computed tomography radiomics predicts HPV status and local tumor control after definitive radiochemotherapy in head and neck squamous cell carcinoma. Int J Radiat Oncol Biol Phys. 2017; 99(4): 921–8. https://doi.org/10.1016/j.ijrobp.2017.06.002.Kuno H, Qureshi MM, Chapman MN, et al. CT texture analysis potentially predicts local failure in head and neck squamous cell carcinoma treated with chemoradiotherapy. Am J Neuroradiol. 2017; 38(12): 2334–40. https://doi.org/10.3174/ajnr.A5407.Kuno H, Qureshi MM, Chapman MN, et al. CT texture analysis potentially predicts local failure in head and neck squamous cell carcinoma treated with chemoradiotherapy. Am J Neuroradiol. 2017; 38(12): 2334–40. https://doi.org/10.3174/ajnr.A5407.Ger RB, Zhou S, Elgohari B, et al. Radiomics features of the primary tumor fail to improve prediction of overall survival in large cohorts of CT- and PET-imaged head and neck cancer patients. PLoS One. 2019; 14(9): e0222509. https://doi.org/10.1371/journal.pone.0222509.Ger RB, Zhou S, Elgohari B, et al. Radiomics features of the primary tumor fail to improve prediction of overall survival in large cohorts of CT- and PET-imaged head and neck cancer patients. PLoS One. 2019; 14(9): e0222509. https://doi.org/10.1371/journal.pone.0222509.Meyer HJ, Hamerla G, Höhn AK, Surov A. CT texture analysiscorrelations with histopathology parameters in head and neck squamous cell carcinomas. Front Oncol. 2019; 9: 444. https://doi.org/10.3389/fonc.2019.00444.Meyer HJ, Hamerla G, Höhn AK, Surov A. CT texture analysiscorrelations with histopathology parameters in head and neck squamous cell carcinomas. Front Oncol. 2019; 9: 444. https://doi.org/10.3389/fonc.2019.00444.Ren J, Qi M, Yuan Y, et al. Machine learning-based MRI texture analysis to predict the histologic grade of oral squamous cell carcinoma. AJR Am J Roentgenol. 2020; 215(5): 1184-90. https://doi.org/10.2214/AJR.19.22593.Ren J, Qi M, Yuan Y, et al. Machine learning-based MRI texture analysis to predict the histologic grade of oral squamous cell carcinoma. AJR Am J Roentgenol. 2020; 215(5): 1184-90. https://doi.org/10.2214/AJR.19.22593.Zhang Y, Chen C, Tian Z, et al. The diagnostic value of MRI-based texture analysis in discrimination of tumors located in posterior fossa: a preliminary study. Front Neurosci Vol. 2019; 13: 1113. https://doi.org/10.3389/fnins.2019.01113.Zhang Y, Chen C, Tian Z, et al. The diagnostic value of MRI-based texture analysis in discrimination of tumors located in posterior fossa: a preliminary study. Front Neurosci Vol. 2019; 13: 1113. https://doi.org/10.3389/fnins.2019.01113.

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