medalphabetМедицинский алфавитMedical alphabet2078-56312949-2807ООО «Альфмед»10.33667/2078-5631-2021-38-14-20medalphabet-2377Research ArticleСтатьиСовременные подходы к устранению артефактов данных конусно-лучевой компьютерной томографии челюстно-лицевой областиModern approaches to the elimination of artifacts of cone-beam computed tomography of the maxillofacial regionhttps://orcid.org/0000-0002-6352-6750ДолгалевА. А.DolgalevA. A.

Долгалев Александр Александрович, д. м.н., доцент, начальник центра инноваций и трансфера технологий, профессор кафедры стоматологии общей практики и детской стоматологии

г. Ставрополь

Dolgalev Al. Al., PhD, MD, Head of the Center for Innovation and Technology Transfer, Professor of the Department of General Practice Dentistry and Pediatric Dentistry

Stavropol

dolgalev@dolgalev.prohttps://orcid.org/0000-0003-4754-3101ДанаевА. Б.DanaevA. B.

Данаев Аслан Барадинович, ассистент кафедры онкологии и лучевой терапии с курсом ДПО

г. Ставрополь

SPIN: 7266-7722

Danaev A.B., assistant of the Department of Oncology and Radiation Therapy with a course of additional professional education

Stavropol

SPIN: 7266-7722. 

aslandanaev111@mail.ruhttps://orcid.org/0000-0002-5410-1849ХоссаинШ. Д.HossainS.J.

Хоссаин Шазмим Джахан, ассистент кафедры челюстно-лицевой хирургии и хирургической стоматологии стоматологииг. Москва

SPIN: 3760-3732

Hossain Shazmim Jahan, DDS, assistant lecturer, the department of oral and maxillofacial surgery

Moscow

SPIN: 3760-3732 

shazmim@mail.ruhttps://orcid.org/0000-0002-7227-9966КуликоваА. А.KulikovaA. A.

Куликова Алёна Алексеевна, учебный мастер кафедры челюстно-лицевой хирургии и хирургической стоматологии

г. Москва

SPIN: 2504-0353

Kulikova A.A., training master of the Oral and maxillofacial surgery Department

Moscow

SPIN: 2504-0353

ЯмурковаН. Ф.YamurkovaN. F.

Ямуркова Нина Федоровна, д. м. н., доцент, заслуженный врач Российской Федерации, челюстно-лицевой хирург высшей категории

г. Нижний Новгород

Yamurkova Nina F., Doctor of Medical Sciences, Associate Professor, Honored Doctor of the Russian Federation, maxillofacial surgeon of the highest category 

Nizhny Novgorod

yamurkova@yandex.ruhttps://orcid.org/0000-0003-2894-6255БуренчевД. В.BurenchevD. V.

Буренчев Дмитрий Владимирович, д.м.н., гл. науч. с.

г. Москва

SPIN: 2411-3959

Burenchev Dmitry V., DM, Chief Researcher

Moscow

SPIN: 2411-3959

dburenchev@mail.ruЧагаровАр. А.ChagarovA. A.

Чагаров Арсен Ахматович, заочный аспирант кафедры стоматологии общей практики и детской стоматологии

г. Ставрополь

Chagarov Arsen A., Postgraduate Student, Department of General Practice and Pediatric Dentistry

Stavropol

Megalowin188@mail.ruСтавропольский Государственный Медицинский УниверситетРоссияStavropol State Medical UniversityRussian FederationФГАОУ ВО «Российский университет дружбы народов»РоссияThe Peoples Friendship University of RussiaRussian FederationГБУЗ НО ГКБ N 39РоссияGBUZ NO GKB N 39Russian FederationГБУЗ «Научно-практический клинический центр диагностики и телемедицинских технологий Департамента здравоохранения города Москвы»РоссияScientific and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Department of HealthcareRussian Federation202124122021138Стоматология (4)1420Copyright © Долгалев А.А., Данаев А.Б., Хоссаин Ш.Д., Куликова А.А., Ямуркова Н.Ф., Буренчев Д.В., Чагаров А.А., 20212021Долгалев А.А., Данаев А.Б., Хоссаин Ш.Д., Куликова А.А., Ямуркова Н.Ф., Буренчев Д.В., Чагаров А.А.Dolgalev A.A., Danaev A.B., Hossain S., Kulikova A.A., Yamurkova N.F., Burenchev D.V., Chagarov A.A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.med-alphabet.com/jour/article/view/2377

Конусно-лучевая компьютерная томография (КЛКТ) занимает основное место в рентгенологической диагностике в стоматологии и челюстно-лицевой хирургии. Мультипланарная и трехмерная реформации данных КЛКТ позволяют провести оценку зоны интереса и выбрать правильную тактику лечения при необходимости. Тем не менее, существует ряд факторов, которые приводят к пространственным искажениям изображений или приводят к потере информации при КЛКТ. В настоящий момент ведутся активные поиски способов улучшения качества изображений КЛКТ и устранения артефактов для повышения диагностической эффективности метода. Данный обзор посвящен описанию основных причин возникновения артефактов и применяемых методов их устранения.

The use of X-ray radiation is the main additional method for complete visualization of hard and soft tissues in dentistry and maxillofacial surgery. Cone-beam computed tomography (CBCT) is of leading importance among other methods. Three-dimensional reformation of CBCT data into a multiplanar or three-dimensional image of anatomical structures allows for a qualitative assessment of the area of interest and to choose the right treatment tactics if necessary. Nevertheless, there are a number of factors or artifacts that lead to distortion, disrupt the image or lead to loss of information during CBCT, in addition, the formation of overdiagnosis is not excluded. Currently, an active search is underway for ways to improve the quality of CBCT images and eliminate artifacts to improve the quality of diagnostics. This review is devoted to the description of the main causes of artifacts and modern methods of their elimination.

КЛКТглубокое машинное обучениеискусственные нейронные сетиартефакты КЛКТCBCTdeep machine learningartificial neural networksCBCT artifactsReferencesBechara B, Alex McMahan C, Moore WS, Noujeim M, Teixeira FB, Geha H (2013) Cone beam CT scans with and without artefact reduction in root fracture detection of endodontically treated teeth. Dentomaxillofacial Radiology. 2013; 42(5): 20120245.Bechara B, Alex McMahan C, Moore WS, Noujeim M, Teixeira FB, Geha H (2013) Cone beam CT scans with and without artefact reduction in root fracture detection of endodontically treated teeth. Dentomaxillofacial Radiology. 2013; 42(5): 20120245.Costa ED, Brasil DM, Queiroz PM, Verner FS, Junqueira RB, Freitas DQ. Use of the metal artefact reduction tool in the identification of fractured endodontic instruments in cone-beam computed tomography. Int Endod J. 2020 Apr;53(4):506-512.Costa ED, Brasil DM, Queiroz PM, Verner FS, Junqueira RB, Freitas DQ. Use of the metal artefact reduction tool in the identification of fractured endodontic instruments in cone-beam computed tomography. Int Endod J. 2020 Apr;53(4):506-512.Katsumata A., Hirukawa A., Okumura S. et al. // Oral Surg. Oral Med. Oral Pathol. Oral Radiol. Endod. –2009. – Vol. 107. – P. 420–425.Katsumata A., Hirukawa A., Okumura S. et al. // Oral Surg. Oral Med. Oral Pathol. Oral Radiol. Endod. –2009. – Vol. 107. – P. 420–425.Наумович С. С., Наумович С. А. Конусно-лучевая компьютерная томография: современные возможности и перспективы применения в стоматологии // Современная стоматология. – 2012. – № 2 (55).Naumovich S.S., Naumovich S.A. Cone beam computed tomography: contemporary possibilities and perspectives of application in dentistry//Sovremennaya stomatologiya. – 2012. – №. 2 (55).Queiroz, Polyane Mazucatto, et al. «Evaluation of metal artefact reduction in cone-beam computed tomography images of different dental materials». Clinical oral investigations 22.1 (2018): 419–423.Queiroz, Polyane Mazucatto, et al. «Evaluation of metal artefact reduction in cone-beam computed tomography images of different dental materials». Clinical oral investigations 22.1 (2018): 419–423.L. Feldkamp, L. Davis, and J. Kress. Practical cone-beam al-gorithm. Journal of the Optical Society of America, 1984; 1(6):612–619.L. Feldkamp, L. Davis, and J. Kress. Practical cone-beam al-gorithm. Journal of the Optical Society of America, 1984; 1(6):612–619.H. Wischmann, H. Luijendijk, H. Meulenbrugge, M. Overdick, R. Schmidt, and K. Kiani, «Correction of amplifier non-linearity, offset gain, temporal artifacts, and defects for flat-planel digital imaging devices» Medical imaging, 2002; vol 4682, p. 427–437.H. Wischmann, H. Luijendijk, H. Meulenbrugge, M. Overdick, R. Schmidt, and K. Kiani, «Correction of amplifier non-linearity, offset gain, temporal artifacts, and defects for flat-planel digital imaging devices» Medical imaging, 2002; vol 4682, p. 427–437.Scarfe, William C., and Allan G. Farman. «What is cone-beam CT and how does it work?» Dental Clinics of North America. 2008; 52(4): 707–730.Scarfe, William C., and Allan G. Farman. «What is cone-beam CT and how does it work?» Dental Clinics of North America. 2008; 52(4): 707–730.Марусина М.Я., Казначеева А.О. Современные виды томографии / Учебное пособие. – СПб: СПБГУ ИТМО, 2006.– 132 с. – 100 экз.Marusina M.J., Treasurer A.O. Modern Types of Tomography / Training Manual. – SPB: SPBG ITMO, 2006. – 132 с. – 100.1990 Recommendations of the International Commission on Radiological Protection. Ann ICRP. 1991;21(1-3):1–201.1990 Recommendations of the International Commission on Radiological Protection. Ann ICRP. 1991;21(1-3):1–201.Sidky EY, Pan X. Image reconstruction in circular cone-beam computed tomography byconstrained, total-variation minimization. Phys. Med. Biol 2008; vol. 53:4777–4807.Sidky EY, Pan X. Image reconstruction in circular cone-beam computed tomography byconstrained, total-variation minimization. Phys. Med. Biol 2008; vol. 53:4777–4807.Patsrisawat T, Gacic A, Franchetti F, Puschel M & Moura JMF in Proceedings. (ICASSP ‘05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005 v/153–v/156 (Philadelphia, PA, USA, 2005).Patsrisawat T, Gacic A, Franchetti F, Puschel M & Moura JMF in Proceedings. (ICASSP ‘05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005 v/153–v/156 (Philadelphia, PA, USA, 2005).Zhu B, Liu JZ, Cauley SF, Rosen BR, Rosen MS. Image reconstruction by domain-transform manifold learning. Nature 2018;555(7697):487.Zhu B, Liu JZ, Cauley SF, Rosen BR, Rosen MS. Image reconstruction by domain-transform manifold learning. Nature 2018;555(7697):487.Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJWL, Biology C, et al. Artificial intelligence in radiology. Nat Rev Cancer. 2018;18(8):500–10.Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJWL, Biology C, et al. Artificial intelligence in radiology. Nat Rev Cancer. 2018;18(8):500–10.Gjesteby, L., Yang, Q., Xi, Y., Zhou, Y., Zhang, J., & Wang, G. (2017, March). Deep learning methods to guide CT image reconstruction and reduce metal artifacts. In Medical Imaging 2017: Physics of Medical Imaging (Vol. 10132, p. 101322W). International Society for Optics and Photonics.Gjesteby, L., Yang, Q., Xi, Y., Zhou, Y., Zhang, J., & Wang, G. (2017, March). Deep learning methods to guide CT image reconstruction and reduce metal artifacts. In Medical Imaging 2017: Physics of Medical Imaging (Vol. 10132, p. 101322W). International Society for Optics and Photonics.Freitas DQ, Fontenele RC, Nascimento EHL, Vasconcelos TV, Noujeim M. Influence of acquisition parameters on the magnitude of cone beam computed tomography artifacts. Dentomaxillofac Radiol. 2018 Dec;47(8):20180151.Freitas DQ, Fontenele RC, Nascimento EHL, Vasconcelos TV, Noujeim M. Influence of acquisition parameters on the magnitude of cone beam computed tomography artifacts. Dentomaxillofac Radiol. 2018 Dec;47(8):20180151.Bezerra ISQ, Neves FS, Vasconcelos TV, Ambrosano GMB, Freitas DQ. Influence of the artefact reduction algorithm of Picasso Trio КЛКТ system on the diagnosis of vertical root fractures in teeth with metal posts. Dentomaxillofac Radiol 2015; 44:1–8.Bezerra ISQ, Neves FS, Vasconcelos TV, Ambrosano GMB, Freitas DQ. Influence of the artefact reduction algorithm of Picasso Trio КЛКТ system on the diagnosis of vertical root fractures in teeth with metal posts. Dentomaxillofac Radiol 2015; 44:1–8.Ezhov M. et al. Clinically applicable artificial intelligence system for dental diagnosis with КЛКТ //Scientific reports. – 2021. – Т. 11. – № 1. – С. 1–16.Ezhov M. et al. Clinically applicable artificial intelligence system for dental diagnosis with КЛКТ //Scientific reports. – 2021. – Т. 11. – № 1. – С. 1–16.Muraev A. A. et al. Frontal cephalometric landmarking: humans vs artificial neural networks //Int J Comput Dent. – 2020. – Т. 23. – № 2. – С. 139–148.Muraev A. A. et al. Frontal cephalometric landmarking: humans vs artificial neural networks //Int J Comput Dent. – 2020. – Т. 23. – № 2. – С. 139–148.Muraev A. A. et al. Искусственные нейронные сети в лучевой диагностике, в стоматологии и в челюстно-лицевой хирургии (обзор литературы) // Клиническая стоматология. – 2020. – № 3. – С. 72–80.Muraev A. A. et al. Искусственные нейронные сети в лучевой диагностике, в стоматологии и в челюстно-лицевой хирургии (обзор литературы) // Клиническая стоматология. – 2020. – № 3. – С. 72–80.Muraev A.A., Kibardin I.A., Oborotistov N. Yu., Ivanov S.S. Use of neural network algorithms for the automated arrangement of cephalometric markers of lateral cefalograms. REJR 2018; 8(4): 16–22.Muraev A.A., Kibardin I.A., Oborotistov N. Yu., Ivanov S.S. Use of neural network algorithms for the automated arrangement of cephalometric markers of lateral cefalograms. REJR 2018; 8(4): 16–22.Способ обучения сверточной нейронной сети осуществлять разметки телерентгенограмм в прямой и боковой проекциях Мураев А.А., Кибардин И.А., Оборотистов Н.Ю., Мураева П.А. Патент на изобретение RU 2717911 C1, 26.03.2020. Заявка № 2019124849 от 06.08.2019.A method of training a convolutional neural network to mark up telerentgenograms in direct and lateral projections Muraev A.A., Kibardin I.A., Oborotistov N.Yu., Muraeva P.A. Patent for invention RU 2717911 C1, 03/26/2020. Application no. 2019124849 dated 06.08.2019.Leite A. F., Vasconcelos K. D. F., Willems H. & Jacobs, R. Radiomics and Machine Learning in Oral Healthcare. PROTEOMICS – Clinical Applications, 2020, p. 1900040.Leite A. F., Vasconcelos K. D. F., Willems H. & Jacobs, R. Radiomics and Machine Learning in Oral Healthcare. PROTEOMICS – Clinical Applications, 2020, p. 1900040.Meyer, E., Bergner, F., Raupach, R., Flohr, T., Kachelrieß M., «Normalized metal artifact reduction (NMAR) in computed tomography». Med. Phys. 37(10), 5482–5493 (2010).Meyer, E., Bergner, F., Raupach, R., Flohr, T., Kachelrieß M., «Normalized metal artifact reduction (NMAR) in computed tomography». Med. Phys. 37(10), 5482–5493 (2010).Zhang Y, Yue N, Su MY, Liu B, Ding Y, Zhou Y, Wang H, Kuang Y, Nie K. Improving CBCT quality to CT level using deep learning with generative adversarial network. Med Phys. 2021 Jun;48(6):2816–2826.Zhang Y, Yue N, Su MY, Liu B, Ding Y, Zhou Y, Wang H, Kuang Y, Nie K. Improving CBCT quality to CT level using deep learning with generative adversarial network. Med Phys. 2021 Jun;48(6):2816–2826.Jiang Z, Chen Y, Zhang Y, Ge Y, Yin FF, Ren L. Augmentation of КЛКТ Reconstructed From Under-Sampled Projections Using Deep Learning. IEEE Trans Med Imaging. 2019 Nov; 38(11):2705–2715.Jiang Z, Chen Y, Zhang Y, Ge Y, Yin FF, Ren L. Augmentation of КЛКТ Reconstructed From Under-Sampled Projections Using Deep Learning. IEEE Trans Med Imaging. 2019 Nov; 38(11):2705–2715.Chen W, Li Y, Yuan N, Qi J, Dyer BA, Sensoy L, Benedict SH, Shang L, Rao S, Rong Y. Clinical Enhancement in AI-Based Post-processed Fast-Scan Low-Dose КЛКТ for Head and Neck Adaptive Radiotherapy. Front Artif Intell. 2021 Feb 11;3:614384.Chen W, Li Y, Yuan N, Qi J, Dyer BA, Sensoy L, Benedict SH, Shang L, Rao S, Rong Y. Clinical Enhancement in AI-Based Post-processed Fast-Scan Low-Dose КЛКТ for Head and Neck Adaptive Radiotherapy. Front Artif Intell. 2021 Feb 11;3:614384.Lei Y, Tang X, Higgins K, Lin J, Jeong J, Liu T, Dhabaan A, Wang T, Dong X, Press R, Curran WJ, Yang X. Learning-based КЛКТ correction using alternating random forest based on auto-context model. Med Phys. 2019 Feb;46(2):601–618.Lei Y, Tang X, Higgins K, Lin J, Jeong J, Liu T, Dhabaan A, Wang T, Dong X, Press R, Curran WJ, Yang X. Learning-based КЛКТ correction using alternating random forest based on auto-context model. Med Phys. 2019 Feb;46(2):601–618.Hammernik, Kerstin, et al. «A deep learning architecture for limitedangle computed tomography reconstruction» Bildverarbeitung für die Medizin 2017. Springer Vieweg, Berlin, Heidelberg, 2017. 92–97.Hammernik, Kerstin, et al. «A deep learning architecture for limitedangle computed tomography reconstruction» Bildverarbeitung für die Medizin 2017. Springer Vieweg, Berlin, Heidelberg, 2017. 92–97.Yang X., Kwitt R., Styner M. and Niethammer M. (2017). Quicksilver: fast predictive image registration – a deep learning approach. NeuroImage 158, 378–396.Yang X., Kwitt R., Styner M. and Niethammer M. (2017). Quicksilver: fast predictive image registration – a deep learning approach. NeuroImage 158, 378–396.

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