Издательский дом "Заславский"

Архів офтальмології та щелепно-лицевої хірургії України Том 1, №1, 2024

Чи можлива повна заміна традиційних цефалометричних аналізів 3D-цефалометрією на основі штучного інтелекту в найближчому майбутньому? (Систематичний огляд)

Авторы: K. Krymovskyy, A. Mileschenko, T. Brychko
Bogomolets National Medical University, Kyiv, Ukraine
Рубрики: Офтальмология

Резюме

Актуальність. Сучасні цефалометричні аналізи надають дані анатомічних вимірювань, що необхідні як для ортодонтів, так і для щелепно-лицевих хірургів. Мета: дослідити точність і ефективність автоматизованого визначення орієнтирів на основі штучного інтелекту (ШІ) для цефалометричного аналізу на двовимірних (2D) бічних цефалограмах та бічних цефалограмах, отриманих із тривимірних (3D) конусно-променевих комп’ютерних томографічних (КПКТ) зображень, у сучасній ортодонтичній практиці. Матеріали та методи. Пошукові дослідження проводили в базах PubMed, Web of Science та Embase за період до 2024 року. Використовували двосторонню стратегію пошуку, яка включала поєднання технічного інтересу (ШI, машинне й глибоке навчання) і діагностичної мети (визначення анатомічних орієнтирів для аналізу рентгенограми черепа). Кожне поняття включало терміни MeSH та ключові слова. Для мінімізації ризику системної помилки був проведений всебічний пошук сірої літератури з використанням таких баз даних, як ProQuest, Google Scholar, OpenThesis і OpenGrey. Результати. Після видалення дублікатів, скринінгу назв і рефератів, повнотекстового читання було відібрано 34 публікації. Серед них у 27 дослідженнях оцінювали точність автоматизованого маркування на 2D бічних цефалограмах на основі ШІ, тоді як 7 досліджень включали 3D-КПКТ зображення. У більшості робот продемонстрований високий ризик системної помилки при виборі даних (n = 27) і референтного стандарту (n = 29). Висновки. ШІ-цефалометричне визначення орієнтирів як на 2D-, так і на бічних цефалограмах, синтезованих із 3D-зображень, показало досить великий потенціал з точки зору точності й ефективності використання часу.

Ключевые слова

ортодонтія; анатомічні орієнтири; цефалометрія; штучний інтелект

Чи можлива повна заміна традиційних цефалометричних аналізів 3D-цефалометрією на основі штучного інтелекту в найближчому майбутньому? (Систематичний огляд) Для просмотра полной версии статьи, пожалуйста войдите или зарегистрируйтесь.
Список литературы

  1. Lavergne J, Gasson N. Les classes II basales étudiées par les réseaux neuronaux. L’Orthodontie Française. 2008;79:91-7. doi: 10.1051/orthodfr:2008004.
  2. Yang S, Eun Sun S, Lee ES, et al. Ceph-Net: automatic detection of cephalometric landmarks on scanned lateral cephalograms from children and adolescents using an attention-based stacked regression network. BMC Oral Health. 2023;23:1-17. doi: 10.1186/s12903-023-03452-7.
  3. Chen R, Ma Y, Chen N, et al. Cephalometric landmark detection by attentive feature pyramid fusion and regression-voting. In: Me–dical Image Computing and Computer Assisted Intervention — MICCAI 2019. Cham: Springer International Publishing; 2019. 873-81. doi: 10.1007/978-3-030-32248-9_97.
  4. Ye H, Cheng Z, Ungvijanpunya N, et al. Is automatic cephalometric software using artificial intelligence better than orthodontist experts in landmark identification? BMC Oral Health. 2023;23:467. doi: 10.1186/s12903-023-03188-4.
  5. Lagravere M, Low C, Flores-Mir C, et al. Intraexaminer and interexaminer reliabilities of landmark identification on digitized lateral cephalograms and formatted 3-dimensional cone-beam computerized tomography images. American Journal of Orthodontics and Dentofacial Orthopedics. 2010;137:598-604. doi: 10.1016/j.ajodo.2008.07.018.
  6. Durao AP, Morosolli A, Pittayapat P, et al. Cephalometric landmark variability among orthodontists and dentomaxillofacial radiologists: a comparative study. Imaging Science in Dentistry. 2015;45:213-20. doi: 10.5624/isd.2015.45.4.213.
  7. Lee JH, Yu HJ, Kim MJ, et al. Automated cephalometric landmark detection with confidence regions using Bayesian convolutio–nal neural networks. BMC Oral Health. 2020;20:270. doi: 10.1186/s12903-020-01256-7.
  8. Schwendicke F, Chaurasia A, Arsiwala L, et al. Deep lear–ning for cephalometric landmark detection: systematic review and meta-analysis. Clinical Oral Investigations. 2021;25:4299-309. doi: 10.1007/s00784-021-03990-w.
  9. Schwendicke F, Samek W, Krois J. Artificial intelligence in dentistry: chances and challenges. Journal of Dental Research. 2020;99:769-74. doi: 10.1177/0022034520915714.
  10. Sarker IH. Deep learning: a comprehensive overview on techniques, taxonomy, applications and research directions. SN Computer Science. 2021;2:420. doi: 10.1007/s42979-021-00815-1.
  11. Chen YJ, Chen SK, Huang HW, et al. Reliability of landmark identification in cephalometric radiography acquired by a storage phosphor imaging system. DentoMaxilloFacial Radiology. 2004;33:301-6. doi: 10.1259/dmfr/85147715.
  12. Mahto RK, Kafle D, Giri A, et al. Evaluation of fully automated cephalometric measurements obtained from web-based artificial intelligence driven platform. BMC Oral Health. 2022;22:132. doi: 10.1186/s12903-022-02170-w.
  13. Serafin M, Baldini B, Cabitza F, et al. Accuracy of automated 3D cephalometric landmarks by deep learning algorithms: systematic review and meta-analysis. La Radiologia Medica. 2023;128:544- 55. doi: 10.1007/s11547-023-01629-2.
  14. Pittayapat P, Bornstein MM, Imada TS, et al. Accuracy of linear measurements using three imaging modalities: two lateral cepha–lograms and one 3D model from CBCT data. European Journal of Orthodontics. 2015;37:202-8. doi: 10.1093/ejo/cju036.
  15. Baldini B, Cavagnetto D, Baselli G, et al. Cephalometric measurements performed on CBCT and reconstructed lateral cephalograms: a cross-sectional study providing a quantitative approach of differences and bias. BMC Oral Health. 2022;22:98. doi: 10.1186/s12903-022-02131-3.
  16. Wang RH, Ho CT, Lin HH, et al. Three-dimensional cepha–lometry for orthognathic planning: normative data and analyses. Journal of the Formosan Medical Association. 2020;119:191-203. doi: 10.1016/j.jfma.2019.04.001.
  17. Nalcaci R, Ozturk F, Sokucu O. A comparison of two-dimensional radiography and three-dimensional computed tomography in angular cephalometric measurements. DentoMaxilloFacial Radiology. 2010;39:100-6. doi: 10.1259/dmfr/82724776.
  18. Page MJ, Moher D, Bossuyt PM, et al. Explanation and elaboration: updated guidance and exemplars for reporting systematic reviews. BMJ. 2021;372:160. doi: 10.1136/bmj.n160.
  19. Whiting PF, Rutjes AWS, Westwood ME, et al; QUADAS-2 Group. QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies. Annals of Internal Medicine. 2011;155:529-36. doi: 10.7326/0003-4819-155-8-201110180-00009.
  20. Reitsma JB, Rutjes A, Whiting P, et al. Chapter 8: Assessing risk of bias and applicability. In: Deeks JJ, Bossuyt PM, Leeflang MM, Takwoingi Y (eds). Cochrane Handbook for Systematic Reviews of Diagnostic Test Accuracy. Version 2.0 (updated July 2023). Cochrane 2023. Available from: https://training.cochrane.org/handbook-diagnostic-test-accuracy/current.
  21. Wang CW, Huang CT, Lee JH, et al. A benchmark for comparison of dental radiography analysis algorithms. Medical Image Analysis. 2016;31:63-76. doi: 10.1016/j.media.2016.02.004.
  22. Lee SM, Kim HP, Jeon K, et al. Automatic 3D cephalometric annotation system using shadowed 2D image-based machine learning. Physics in Medicine and Biology. 2019;64:055002. doi: 10.1088/1361-6560/ab00c9.
  23. Lang Y, Lian C, Xiao D, et al. Localization of cranioma–xillofacial landmarks on CBCT images using 3D mask R-CNN and local dependency learning. IEEE Transactions on Medical Imaging. 2022;41:2856-66. doi: 10.1109/TMI.2022.3174513.
  24. Yun HS, Hyun CM, Baek SH, et al. A semi-supervised lear–ning approach for automated 3D cephalometric landmark identification using computed tomography. PLoS One. 2022;17:e0275114. doi: 10.1371/journal.pone.0275114.
  25. Hwang HW, Moon JH, Kim MG, et al. Evaluation of automated cephalometric analysis based on the latest deep learning method. The Angle Orthodontist. 2021;91:329-35. doi: 10.2319/021220-100.1.
  26. Yun HS, Jang TJ, Lee SM, et al. Learning-based local-to-glo–bal landmark annotation for automatic 3D cephalometry. Physics in Medicine and Biology. 2020;65:085018. doi: 10.1088/1361-6560/ab7a71.
  27. Arik SO, Ibragimov B, Xing L. Fully automated quantitative cephalometry using convolutional neural networks. Journal of Medical Imaging (Bellingham). 2017;4:014501. doi: 10.1117/1. JMI.4.1.014501.
  28. Qian JH, Luo WZ, Cheng M, et al. CephaNN: A multi-head attention network for cephalometric landmark detection. IEEE Access. 2020;8:112633-641.
  29. Song Y, Qiao X, Iwamoto Y, et al. Automatic cephalometric landmark detection on X-ray images using a deep-learning method. Applied Sciences-Basel. 2020;10:2547. doi: 10.3390/app10072547.
  30. Yao J, Zeng W, He T, et al. Automatic localization of cephalometric landmarks based on convolutional neural network. American Journal of Orthodontics and Dentofacial Orthopedics. 2022;161:e250-9. doi: 10.1016/j.ajodo.2021.09.012.
  31. Ma Q, Kobayashi E, Fan B, et al. Automatic 3D landmarking model using patch-based deep neural networks for CT image of oral and maxillofacial surgery. The International Journal of Medical Robotics. 2020;16:2093. doi: 10.1002/rcs.2093.
  32. Kwon H, Koo H, Park J, et al. Multistage probabilistic approach for the localization of cephalometric landmarks. IEEE Access. 2021;9:21306-14.
  33. Steiner CC. Cephalometrics for you and me. American Journal of Orthodontics. 1953;39:729-55. doi: 10.1016/0002-9416(53)90082-7.
  34. Downs W. The role of cephalometrics in orthodontic case ana–lysis and diagnosis. American Journal of Orthodontics. 1952;38:20.
  35. Addo PM. Artificial intelligence, developing-country science and bilateral co-operation, in OECD, Artificial Intelligence in Science: Challenges, Opportunities and the Future of Research. OECD. Paris: OECD Publishing; 2023. doi: 10.1787/4edb761e-en.
  36. Hankins E, Nettel PF, Martinescu L, et al. Government AI readiness index 2023. Oxford Insights; 2023. Available from: https://oxfordinsights.com/ai-readiness/ai-readiness-index/.
  37. Renard F, Guedria S, Palma N, et al. Variability and reproducibility in deep learning for medical image segmentation. Scientific Reports. 2020;10:13724. doi: 10.1038/s41598-020-69920-0.
  38. Eche T, Schwartz LH, Mokrane FZ, et al. Toward generali–zability in the deployment of artificial intelligence in radiology: role of computation stress testing to overcome under specification. Radiology Artificial Intelligence. 2021;3:210097. doi: 10.1148/ryai.2021210097.
  39. Le VNT, Kang J, Oh IS, et al. Effectiveness of human-artificial intelligence collaboration in cephalometric landmark detection. Journal of Personalized Medicine. 2022;12:387. doi: 10.3390/jpm12030387.
  40. Tanikawa C, Oka A, Lim J, et al. Clinical applicability of automated cephalometric landmark identification: Part II — Number of images needed to re-learn various quality of images. Orthodontics and Craniofacial Research. 2021;24:53-8. doi: 10.1111/ocr.12511.
  41. Darkwah WK, Kadri A, Adormaa BB, et al. Cephalometric study of the relationship between facial morphology and ethnicity: review article. Translational Research in Anatomy. 2018;12:20-4. doi: 10.1016/j.tria.2018.07.001.
  42. Kim H, Shim E, Park J, et al. Web-based fully automa–ted cephalometric analysis by deep learning. Computer Methods and Programs in Biomedicine. 2020;194:105513. doi: 10.1016/j. cmpb.2020.105513.
  43. Wang CW, Huang CT, Hsieh MC, et al. Evaluation and comparison of anatomical landmark detection methods for cephalometric X-ray images: a grand challenge. IEEE Transactions on Medical Ima–ging. 2015;34:1890-900. doi: 10.1109/TMI.2015.2412951.
  44. Tanikawa C, Lee C, Lim J, et al. Clinical applicability of automated cephalometric landmark identification: Part I — Patient-related identification errors. Orthodontics and Craniofacial Research. 2021;24:43-52. doi: 10.1111/ocr.12501.
  45. Schlicher W, Nielsen I, Huang JC, et al. Consistency and precision of landmark identification in three-dimensional cone beam computed tomography scans. European Journal of Orthodontics. 2012;34:263-75. doi: 10.1093/ejo/cjq144.
  46. Verhelst PJ, Smolders A, Beznik T, et al. Layered deep lear–ning for automatic mandibular segmentation in cone-beam computed tomography. Journal of Dentistry. 2021;114:103786. doi: 10.1016/j.jdent.2021.103786.
  47. Preda F, Morgan N, Van Gerven A, et al. Deep convolutional neural network-based automated segmentation of the maxillofacial complex from cone-beam computed tomography: a validation study. Journal of Dentistry. 2022;124:104238. doi: 10.1016/j. jdent.2022.104238.
  48. Chien PC, Parks E, Eraso F, et al. Comparison of reliability in anatomical landmark identification using two-dimensional digital cephalometrics and three-dimensional cone beam computed tomo–graphy in vivo. DentoMaxilloFacial Radiology. 2009;38:262-73. doi: 10.1259/dmfr/81889955.
  49. De Queiroz Tavares Borges Mesquita G, Vieira WA, Vidigal MTC, et al. Artificial intelligence for detecting cephalometric landmarks: a systematic review and meta-analysis. Journal of Digital Ima–ging. 2023;36:1158-79. doi: 10.1007/s10278-022-00766-w.
  50. Schwendicke F, Krois J. Better reporting of studies on artificial intelligence: CONSORT-AI and beyond. Journal of Dental Research. 2021;100:677-80. doi: 10.1177/0022034521998337.
  51. Bulatova G, Kusnoto B, Grace V, et al. Assessment of automa–tic cephalometric landmark identification using artificial intelligence. Orthodontics and Craniofacial Research. 2021;24:37-42. doi: 10.1111/ocr.12542.
  52. Chen J, Che H, Sun J, et al. An automatic cephalometric landmark detection method based on heatmap regression and Monte Carlo dropout. Annual International Conference of the IEEE Enginee–ring in Medicine and Biology Society. 2023;2023:1-4. doi: 10.2139/ssrn.4184448.
  53. Hong W, Kim SM, Choi J, et al. Automated cephalometric landmark detection using deep reinforcement learning. The Journal of Craniofacial Surgery. 2023;34:2336-42. doi: 10.1097/ SCS.0000000000009685.
  54. Huang Y, Fan F, Syben C, et al. Cephalogram synthesis and landmark detection in dental cone-beam CT systems. Medical Image Analysis. 2021;70:102028. doi: 10.1016/j.media.2021.102028.
  55. Kim MJ, Liu Y, Oh SH, et al. Automatic cephalometric landmark identification system based on the multi-stage convolutional neural networks with CBCT combination images. Sensors (Basel). 2021;21:505. doi: 10.3390/s21020505.
  56. Kim YH, Lee C, Ha EG, et al. A fully deep learning model for the automatic identification of cephalometric landmarks. Imaging Science in Dentistry. 2021;51:299-306. doi: 10.5624/isd.20210077.
  57. Lee M, Chung M, Shin YG. Cephalometric landmark detection via global and local encoders and patch-wise attentions. Neurocomputing. 2022;470:182-9. doi: 10.1016/j.neucom.2021.11.003.
  58. Noothout JMH, De Vos BD, Wolterink JM, et al. Deep lear–ning-based regression and classification for automatic landmark loca–lization in medical images. IEEE Transactions on Medical Imaging. 2020;39:4011-22. doi: 10.1109/TMI.2020.3009002.
  59. Oh K, Oh IS, Le VNT, et al. Deep anatomical context feature learning for cephalometric landmark detection. IEEE Journal of Biomedical Health Informatics. 2021;25:806-17. doi: 10.1109/JBHI.2020.3002582.
  60. Park JH, Hwang HW, Moon JH, et al. Automated identification of cephalometric landmarks: Part 1 — Comparisons between the latest deep-learning methods YOLOV3 and SSD. The Angle Orthodontist. 2019;89:903-9. doi: 10.2319/022019-127.1.
  61. Song Y, Qiao X, Iwamoto Y, et al. An efficient deep learning based coarse-to-fine cephalometric landmark detection method. IECIE Transactions on Information and Systems. 2021;E104.D:1359-66. doi: 10.1587/transinf.2021edp7001.
  62. Uğurlu M. Performance of a convolutional neural network-based artificial intelligence algorithm for automatic cephalometric landmark detection. Turkish Journal of Orthodontics. 2022;35:94-100. doi: 10.5152/TurkJOrthod.2022.22026.
  63. Wang L, Ma L, Li Y, et al. A DCNN system based on an itera–tive method for automatic landmark detection in cephalometric X-ray images. Biomedical Signal Processing and Control. 2021;68:102757. doi: 10.1016/j.bspc.2021.102757.
  64. Zeng M, Yan Z, Liu S, et al. Cascaded convolutional networks for automatic cephalometric landmark detection. Medical Image Ana–lysis. 2021;68:101904. doi: 10.1016/j.media.2020.101904.
  65. Zhao C, Yuan Z, Luo S, et al. Automatic recognition of cephalometric landmarks via multi-scale sampling strategy. Heliyon. 2023;9:e17459. doi: 10.1016/j.heliyon.2023.e17459.
  66. Zhong Z, Li J, Zhang Z, et al. An attention-guided deep regression model for landmark detection in cephalograms. In: Medical Image Computing and Computer Assisted Intervention — MICCAI 2019. Cham: Springer International Publishing; 2019. 540-8. doi: 10.1007/978-3-030-32226-7_60.
  67. Dot G, Schouman T, Chang S, et al. Automatic 3-dimensional cephalometric landmarking via deep learning. Journal of Dental Research. 2022;101:1380-7. doi: 10.1177/00220345221112333.
  68. Weingart JV, Schlager S, Metzger MC, et al. Automated detection of cephalometric landmarks using deep neural patchworks. DentoMaxilloFacial Radiology. 2023;52:20230059. doi: 10.1259/dmfr.20230059.