Opportunistic screening of osteoporosis using artificial intelligence services



Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

BACKGROUND: An approach to the diagnosis of osteoporosis (OP) based on CT scans examination is being implemented. When performing CT scans, the signs of OP can be detected. There is a problem with underdiagnosing compression fractures (CFs) using CT scans. It is recommended to use artificial intelligence (AI-service) radiologist’s assistant.

AIM: To evaluate a possibility of the application of artificial intelligence services into a practice of the diagnosis of OP based on routine CT scans to implement opportunistic screening.

MATERIALS AND METHODS: Three medical facilities (MF) participated in the project. We selected chest CT of patients over 50 years old, for whom AI services identified signs of OP (compression fractures (CFs) and/or decreased X-ray density of vertebral bodies) which were performed for the period from October 2022 to October 2023. They were subsequently validated by radiologists for the presence of target pathology. A final list of patients, who needed to undergo dual-energy X-ray absorptiometry (DXA) to confirm the diagnosis of OP, was sent to the attending physician at the MF.

RESULTS: 5,394 CT studies were analyzed by AI services in 12 months. CFs and/or decreased X-ray density of vertebral bodies were detected in 1125 patients. Patients with a previous diagnosis of OP, as well as who refused or could not attend the additional examination were excluded. 66 patients underwent DXA. The patients’ age ranged from 54 to 86 (median age was 70 (62–74), male to female ratio was 21%; 79%. According to DXA, 26 (39.4%) of the examined patients had bone mineral density (BMD) indicators corresponded to OP, in 37 patients (56.1%) BMD indicators corresponded to osteopenia, and only in three (4.54%) — BMD indicators corresponded to the norm. The accuracy metrics of the DXA methods and the assessment of X-ray density of vertebral bodies by CT were calculated: sensitivity — 0.71 and 0.91; specificity — 0.80 and 0.55; accuracy — 0.76 and 0.67.

Statistically significant differences between different conditions and belonging of patients to the group of “age norm” and the group of patients allocated by AI services were demonstrated (p <0.001).

CONCLUSIONS: The obtained study results indicate the expediency of using AI services for the diagnosis of OP based on routine CT scans as a component of opportunistic screening.

Full Text

Funding source. This article was prepared by the authors as part of the research and development work (EGISU number: 123031400007-7) in accordance with the Program of the Moscow Department of Health for 2023-2025.

Competing interests. The authors declare that they have no competing interests.

Author contribution: All authors made a substantial contribution to the conception of the work, acquisition, analysis, interpretation of data for the work, drafting and revising the work, final approval of the version to be published and agree to be accountable for all aspects of the work. Artyukova Z.R., Kudryavtsev N.D. – writing the text of the article, performing the experimental part of the research, validation; Petraikin A.V., Semenov D.S. – data analysis; Vladzymyrskyy A.V., Vasilev Yu.A. – study concept and design.

 

Fig. 1. Scheme of the pilot study. Abbreviations: DXA – dual-energy X-ray absorptiometry; AI –  artificial intelligence; CD – compression deformation; CF – compression fracture; chest CT – computed tomography of chest organs; MF – medical facility; BMD – bone mineral density; OP – osteoporosis; XRD – X-ray density

Fig. 2. Screening example (a woman, 84 years old): A) An additional CT-imagine series; B) DXA of the lumbar spine and the proximal femur (left and right). The patient underwent a chest CT in January 2023. The CT-scan was analyzed by the AI service (Genant-IRA), wich determined signs of OP – CD of vertebral body Th12 to 32%; XRD of vertebral body Th11, L1, L2 less than 100 HU. The patient underwent the additional DXA in May 2023. According to DXA, the BMD corresponds to OP

Fig. 3. Results obtained from DXA

Fig. 4. Distribution by sex and mineral density in patients who underwent DXA

×

About the authors

Zlata Artyukova

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Health Care Department

Author for correspondence.
Email: zl.artyukova@gmail.com
ORCID iD: 0000-0003-2960-9787
Russian Federation

Nikita D. Kudryavtsev

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: KudryavtsevND@zdrav.mos.ru
ORCID iD: 0000-0003-4203-0630
SPIN-code: 1125-8637
Russian Federation, Moscow

Alexey V. Petraikin

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: alexeypetraikin@gmail.com
ORCID iD: 0000-0003-1694-4682
SPIN-code: 6193-1656

MD, Dr. Sci. (Med.), Associate Professor,

Russian Federation, Moscow

Dmitry S. Semenov

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: SemenovDS4@zdrav.mos.ru
ORCID iD: 0000-0002-4293-2514
SPIN-code: 2278-7290

Cand. Sci. (Engineering)

Russian Federation, Moscow

Anton A. Vladzymyrskyy

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: VladzimirskijAV@zdrav.mos.ru
ORCID iD: 0000-0002-2990-7736
SPIN-code: 3602-7120

MD, Dr. Sci. (Med.)

Russian Federation, Moscow

Yuriy A. Vasilev

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: VasilevYA1@zdrav.mos.ru
ORCID iD: 0000-0002-5283-5961
SPIN-code: 4458-5608

MD, Cand. Sci. (Med.)

Russian Federation, Moscow

References

  1. Belaya ZhE, Belova KYu, Biryukova EV, et al. Federal clinical guidelines for diagnosis, treatment and prevention of osteoporosis. Osteoporosis and Bone Diseases. 2021;24(2):4–47. doi: 10.14341/osteo12930 EDN: TUONYE
  2. The International Society For Clinical Densitometry (ISCD). The Adult Official Positions of the ISCD. 2023. Available from: https://iscd.org/official-positions-2023/ Accessed: Apr 18, 2023.
  3. Petryaikin AV, Artyukova ZR, Nizovtsova LA, et al. M 54 Methodological recommendations for conducting dual-energy X-ray absorptiometry. Moscow: GBUZ "NPCC DiT DZM"; 2022. 60 p. (In Russ.).
  4. Alacreu E, Moratal D, Arana E. Opportunistic screening for osteoporosis by routine CT in Southern Europe // Osteoporosis International. 2017;28(3):983–990. doi: 10.1007/s00198-016-3804-3
  5. Gossner J. Missed incidental vertebral compression fractures on computed tomography imaging: More optimism justified. World J Radiol. 2010;21(2):472–473. doi: 10.4329/wjr.v2.i12.472
  6. Carberry GA, Pooler BD, Binkley N, et al. Unreported vertebral body compression fractures at abdominal multidetector CT. Radiology. 2013;268(1):120–126. doi: 10.1148/radiol.13121632
  7. Vasiliev YuA, Vladzimirsky AV. Computer vision in radiation diagnostics: the first stage of the Moscow Experiment. Moscow: Publishing Solution; 2023. (In Russ.).
  8. Pisov M, Kondratenko V, Zakharov A, et al. Keypoints Localization for Joint Vertebra Detection and Fracture Severity Quantification. Lecture Notes in Computer Science. 2020;12266:723–732. doi: 10.1007/978-3-030-59725-2_70
  9. Tomita N, Cheung YY, Hassanpour S. Deep neural networks for automatic detection of osteoporotic vertebral fractures on CT scans. Computers in Biology and Medicine. 2018;98:8–15. doi: 10.1016/j.compbiomed.2018.05.011
  10. Cheng X, Zhao K, Zha X, et al. Opportunistic Screening Using Low‐Dose CT and the Prevalence of Osteoporosis in China: A Nationwide, Multicenter Study. Journal of Bone and Mineral Research. 2021;36(3):427–435. doi: 10.1002/jbmr.4187
  11. Artificial intelligence services in radiation diagnostics. 2023. Available from: https://mosmed.ai/ Accessed: Apr 18, 2023. (In Russ.).
  12. Genant HK, Wu CY, van Kuijk C, et al. Vertebral fracture assessment using a semiquantitative technique. J Bone Miner Res. 1993;8(9):1137–48. doi: 10.1002/jbmr.5650080915
  13. Petryaikin AV, Belaya ZhE, Belyaev MG, et al. Accuracy of automatic diagnostics of compression fractures of vertebral bodies according to the morphometric algorithm of artificial intelligence. Osteoporosis and Bone Diseases. 2022;25(3):92–93. (In Russ.). doi: 10.14341/osteo13064
  14. Petraikin AV, Artyukova ZR, Kudryavtsev ND, et al. Analysis of Age Distribution of Bone Mineral Density by Dual-Energy X-Ray Absorptiometry. Journal of Radiology and Nuclear Medicine. 2023;104(1):21–29. doi: 10.20862/0042-4676-2023-104-1-21-29 EDN: ULUKYU
  15. Lesnyak OM, Yershova OB, Zakroeva AG, et al. Audit of the Russian Osteoporosis Association. 2020. Р. 44. (In Russ.).
  16. Salari N, Ghasemi H, Mohammadi L, et al. The global prevalence of osteoporosis in the world : a comprehensive systematic review and meta-analysis. Journal of Orthopaedic Surgery and Research. 2021;16(1):609. doi: 10.1186/s13018-021-02772-0
  17. Murata K, Endo K, Aihara T, et al. Artificial intelligence for the detection of vertebral fractures on plain spinal radiography. Sci Rep. 2020;10(1):20031. doi: 10.1038/s41598-020-76866-w
  18. Dong Q, Luo G, Lane NE, et al. Deep Learning Classification of Spinal Osteoporotic Compression Fractures on Radiographs using an Adaptation of the Genant Semiquantitative Criteria. Acad Radiol. 2022;29(12):1819–1832. doi: 10.1016/j.acra.2022.02.020
  19. Valentinitsch A, Trebeschi S, Kaesmacher J, et al. Opportunistic osteoporosis screening in multi-detector CT images via local classification of textures. Osteoporos Int. 2019;30(6):1275–1285. doi: 10.1007/s00198-019-04910-1
  20. Yasaka K, Akai H, Kunimatsu A, et al. Prediction of bone mineral density from computed tomography: application of deep learning with a convolutional neural network. Eur Radiol. 2020;30(6):3549–3557. doi: 10.1007/s00330-020-06677-0
  21. Nam KH, Seo I, Kim DH, et al. Machine Learning Model to Predict Osteoporotic Spine with Hounsfield Units on Lumbar Computed Tomography. J Korean Neurosurg Soc. 2019;62(4):442–449. doi: 10.3340/jkns.2018.0178
  22. Zhang J, Liu J, Liang Z, et al. Differentiation of acute and chronic vertebral compression fractures using conventional CT based on deep transfer learning features and hand-crafted radiomics features. BMC Musculoskeletal Disorders. 2023;24(1):165. doi: 10.1186/s12891-023-06281-5
  23. Certificate of State registration of the database No. 2023621171 Russian Federation. Vasiliev YuA, Turavilova EV, Vladzimirsky AV, et al. MosMedData: CT scan with signs of spinal osteoporosis. The applicant is the State Budgetary Healthcare Institution of the city of Moscow "Scientific and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Department of Healthcare of the City of Moscow". Registration date: 04/11/2023. (In Russ.).
  24. Vasiliev YuA, Vlazimirsky AV, Omelyanskaya OV, et al. Methodology for testing and monitoring artificial intelligence-based software for medical diagnostics. Digital Diagnostics. 2023;4(3):252−267. doi: https://doi.org/10.17816/DD321971 EDN: UEDORU
  25. Bobrovskaya TM, Kirpichev YS, Savkina EF, Chetverikov SF, Arzamasov KM. Development and validation of a tool for statistical comparison of roc-curves using the example of algorithms based on artificial intelligence technologies Medical doctor and information technologies. 2023;3:4–15. doi: 10.25881/18110193_2023_3_4 EDN: CUFICX
  26. Artyukova ZR, Kudryavtsev ND, Petraikin AV, et al. Using an artificial intelligence algorithm to assess the bone mineral density of the vertebral bodies based on computed tomography data. Medical Visualization. 2023;27(2):125–137. doi: 10.24835/1607-0763-1257 EDN: FQACCV
  27. Petraikin AV, Belaya ZhE, Kiseleva AN, et al. Artificial intelligence for diagnosis of vertebral compression fractures using a morphometric analysis model, based on convolutional neural networks. Problems of Endocrinology. 2020;66(5):48–60. doi: 10.14341/probl12605 EDN: GLXSYG
  28. Löffler MT, Jacob A, Scharr A, et al. Automatic opportunistic osteoporosis screening in routine CT: improved prediction of patients with prevalent vertebral fractures compared to DXA. Eur Radiol. 2021;31(8):6069–6077. doi: 10.1007/s00330-020-07655-2
  29. Petraikin AV, Toroptsova NV, Nikitsinskaya OA, et al. Using asynchronous quantitative computed tomography for opportunistic screening of osteoporosis. Rheumatology Science and Practice. 2022;60(3):360–368. doi: 10.47360/1995-4484-2022-360-368 EDN: KTYJHB
  30. Mikhailov EE, Benevolenskaya LI. Epidemiology of osteoporosis and fractures. In: A Guide to Osteoporosis. Moscow: BINOM. Laboratory of Knowledge; 2003: 10–55. (In Russ.).
  31. Morozov SP, Gavrilov AV, Arkhipov IV, et al. Effect of artificial intelligence technologies on the CT scan interpreting time in COVID-19 patients in inpatient setting. Russian Journal of Preventive Medicine. 2022;25(1):14–20. doi: 10.17116/profmed20222501114 EDN: QRZZKS
  32. Vladzymyrskyy AV, Kudryavtsev ND, Kozhikhina DD, et al. Effectiveness of using artificial intelligence technologies for dual descriptions of the results of preventive lung examinations. Russian Journal of Preventive Medicine. 2022;25(7):7–15. doi: 10.17116/profmed2022250717 EDN: JNUMFN

Supplementary files

Supplementary Files
Action
1. JATS XML
Download

Copyright (c) Eco-Vector


СМИ зарегистрировано Федеральной службой по надзору в сфере связи, информационных технологий и массовых коммуникаций (Роскомнадзор).
Регистрационный номер и дата принятия решения о регистрации СМИ: серия ПИ № ФС 77-76249 от 19.07.2019.