The first step of artificial intelligence in dental practice: Segmentation applications

Year 2023, Volume: 33 Issue: 1, 40 - 49, 31.01.2023

Elif Şener Barış Oğuz Gürses

https://doi.org/10.17567/ataunidfd.899222

Abstract

Diş hekimliği pratiğinde yapay zekanın ilk basamağı: Segmentasyon uygulamaları
3 boyutlu (3B) görüntüleme tekniklerinin dişhekimliği pratiğinde kullanımının artışı, gerek medikal gerekse dental tanı ve tedavi planlamasında yararlanılacak yapay zeka uygulamaları aşamasında 3B görüntü temelli bilgisayar destekli görüntü analiz yöntemlerinin kullanımını hızlandırmıştır. Görüntü verileri kullanılarak anatomik yapıların segmentasyon işleminin gerçekleştirilmesi tıbbi modelle- menin temeli olup; X ışını temelli görüntü analizi sürecinin önemli bir parçasını oluşturur. Görüntü veri analizinin yüksek doğrulukla gerçekleştirilmesi aşamasında segmentasyon işleminin doğru ve yeterli şekilde yapılma zorunluluğu, segmentasyon yöntemlerinin hassasiyetinin medikal tomografi ve dental volümetrik tomografi (DVT) cihazları kullanılarak gerçekleştirilen çalışmalarda irdelenme- sine neden olmuştur. Bu çalışmanın amacı; dişhekimliğinin birçok farklı disiplininde kullanılan temel segmantasyon tekniklerini tanıtmak, mevcut avantaj, dezavantaj ve sınırılıklarını tartışmaktır.
Anahtar Kelimeler: yapay zeka, görüntü segmentasyon yöntemleri, dental volümetrik tomografi (DVT), dental
ABSTRACT
The increasing use of 3-dimensional imaging techniques in dental practice has boosted the devel- opment and employment of 3-dimensional image-based computer-aided analysis for implemen- tation of artificial intelligence into medical/dental diagnosis and management. Segmentation of anatomical structures using image data is the basis of medical modeling and an important part of the x-ray-based image analysis process. Since an accurate and efficient segmentation approach is required for appropriate image data analysis, the precision of segmentation methods has been tested in many studies using multislice computed tomography and more recently by dental volumetric tomography. The aim of this review paper is to present main image segmentation approaches which have been used in many disciplines of dentistry and to discuss their advan- tages, disadvantages, and limitations.
Keywords: Artificial intelligence, image segmentation methods, dental volumetric tomography (DVT), dental

Keywords

Artificial intelligence, image segmentation methods, dental volumetric tomography (DVT)

Diş hekimliği pratiğinde yapay zekanın ilk basamağı: Segmentasyon uygulamaları

Abstract

3 boyutlu (3B) görüntüleme tekniklerinin dişhekimliği pratiğinde kullanımının artışı, gerek medikal gerekse dental tanı ve tedavi planlamasında yararlanılacak yapay zeka uygulamaları aşamasında 3B görüntü temelli bilgisayar destekli görüntü analiz yöntemlerinin kullanımını hızlandırmıştır. Görüntü verileri kullanılarak anatomik yapıların segmentasyon işleminin gerçekleştirilmesi tıbbi modelle- menin temeli olup; X ışını temelli görüntü analizi sürecinin önemli bir parçasını oluşturur. Görüntü veri analizinin yüksek doğrulukla gerçekleştirilmesi aşamasında segmentasyon işleminin doğru ve yeterli şekilde yapılma zorunluluğu, segmentasyon yöntemlerinin hassasiyetinin medikal tomografi ve dental volümetrik tomografi (DVT) cihazları kullanılarak gerçekleştirilen çalışmalarda irdelenme- sine neden olmuştur. Bu çalışmanın amacı; dişhekimliğinin birçok farklı disiplininde kullanılan temel segmantasyon tekniklerini tanıtmak, mevcut avantaj, dezavantaj ve sınırılıklarını tartışmaktır.
Anahtar Kelimeler: yapay zeka, görüntü segmentasyon yöntemleri, dental volümetrik tomografi (DVT), dental

ABSTRACT
The increasing use of 3-dimensional imaging techniques in dental practice has boosted the devel- opment and employment of 3-dimensional image-based computer-aided analysis for implemen- tation of artificial intelligence into medical/dental diagnosis and management. Segmentation of anatomical structures using image data is the basis of medical modeling and an important part of the x-ray-based image analysis process. Since an accurate and efficient segmentation approach is required for appropriate image data analysis, the precision of segmentation methods has been tested in many studies using multislice computed tomography and more recently by dental volumetric tomography. The aim of this review paper is to present main image segmentation approaches which have been used in many disciplines of dentistry and to discuss their advan- tages, disadvantages, and limitations.
Keywords: Artificial intelligence, image segmentation methods, dental volumetric tomography (DVT), dental

Keywords

yapay zeka, görüntü segmentasyon yöntemleri, dental volümetrik tomografi (DVT)

References

• 1. Pham DL, Xu C, Prince JL. Current methods in medical image seg- mentation. Annu Rev Biomed Eng. 2000;2(1):315-337. [CrossRef]
• 2. Pal NR, Pal SK. A review on image segmentation techniques. Pattern Recognit. 1993;26(9):1277-1294. [CrossRef]
• 3. Olabarriaga SD, Smeulders AWM. Interaction in the segmentation of medical images: A survey. Med Image Anal. 2001;5(2):127-142. [CrossRef]
• 4. Withey DJ, Koles ZJ. Three generations of medical image segmenta- tion: Methods and available software. Int J Bioelectromag. 2007; 9:67-68.
• 5. Gunamani JR, Baliarsingh Sabuj Kr, Jena PGMV. Image segmentation using Gabor transform and S- transform. In 2006 International Con- ference on Advanced Computing and Communications. Mangalore, India: IEEE; 2006:618-619.
• 6. Payel R, Saurab D, Nilanjan D, Goutami D, Chakraborty S, Ruben R. Adaptive thresholding: A comparative study. In 2014 International Conference on Control, Instrumentation, Communication and Com- putational Technologies (ICCICCT). Kanyakumari District, India: IEEE; 2014:1182-1186. 7. Muthukrishnan R, Radha M. Edge detection techniques for image segmentation. Int J Comput Sci Inf Technol. 2011;3(6):259-267. [CrossRef]
• 8. Galibourg A, Dumoncel J, Telmon N, Calvet A, Michetti J, Maret D. Assessment of automatic segmentation of teeth using a watershed- based method. Dento Maxillo Facial Rad. 2018;47(1):20170220. [CrossRef]
• 9. Premaladha J, Ravichandran KS. Novel approaches for diagnosing melanoma skin lesions through supervised and deep learning algo- rithms. J Med Syst. 2016;40(4):96. [CrossRef]
• 10. Kharazmi P, Zheng J, Lui H, Jane Wang ZJ, Lee TK. A computer-aided decision support system for detection and localization of cutaneous vasculature in dermoscopy images via deep feature learning. J Med Syst. 2018;42(2):33. [CrossRef]
• 11. Deng L, Yu D. Deep learning: Methods and applications. Found Trends. 2014;7(3-4):197-387. [CrossRef]
• 12. Işın A, Direkoğlu C, Şah M. Review of MRI-based brain tumor image segmentation using deep learning methods. Procedia Comput Sci. 2016;102:317-324. [CrossRef]
• 13. Hashempour N, Tuulari JJ, Merisaari H, et al. A novel approach for manual segmentation of the amygdala and hippocampus in neonate MRI. Front Neurosci. 2019;13:1025. [CrossRef]
• 14. Emblem KE, Nedregaard B, Hald JK, Nome T, Due-Tonnessen P, Bjornerud A. Automatic glioma characterization from dynamic sus- ceptibility contrast imaging: Brain tumor segmentation using knowledge-based fuzzy clustering. J Magn Reson Imaging. 2009; 30(1):1-10. [CrossRef]
• 15. Hung K, Yeung AWK, Tanaka R, Bornstein MM. Current applications, opportunities, and limitations of AI for 3D imaging in dental research and practice. Int J Environ Res Public Health. 2020;17(12):4424. [CrossRef]
• 16. Chin SJ, Wilde F, Neuhaus M, Schramm A, Gellrich NC, Rana M. Accu- racy of virtual surgical planning of orthognathic surgery with aid of CAD/CAM fabricated surgical splint-A novel 3D analyzing algorithm. J Craniomaxillofac Surg. 2017;45(12):1962-1970. [CrossRef]
• 17. Aboul-Hosn Centenero S, Hernández-Alfaro F. 3D planning in orthognathic surgery: CAD/CAM surgical splints and prediction of the soft and hard tissues results - our experience in 16 cases. J Cra- niomaxillofac Surg. 2012;40(2):162-168. [CrossRef]
• 18. Queiroz PM, Rovaris K, Santaella GM, Haiter-Neto F, Freitas DQ. Comparison of automatic and visual methods used for image seg- mentation in endodontics: A microCT study. J Appl Oral Sci. 2017; 25(6):674-679. [CrossRef]
• 19. Gerlach NL, Meijer GJ, Kroon DJ, Bronkhorst EM, Bergé SJ, Maal TJ. Evaluation of the potential of automatic segmentation of the man- dibular canal using cone-beam computed tomography. Br J Oral Maxillofac Surg. 2014;52(9):838-844. [CrossRef]
• 20. Wang L, Li S, Chen R, Liu SY, Chen JC. An automatic segmentation and classification framework based on PCNN model for single tooth in MicroCT images. PLoS One. 2016;11(6):e0157694. [CrossRef]
• 21. Mohan G, Subashini MM. MRI based medical image analysis: Survey on brain tumor grade classification. Biomed Signal Process Control. 2018;39:139-161. [CrossRef]
• 22. Rastegar B, Thumilaire B, Odri GA, et al. Validation of a windowing protocol for accurate in vivo tooth segmentation using i-CAT cone beam computed tomography. Adv Clin Exp Med. 2018;27(7): 1001-1008. [CrossRef]
• 23. Schloss T, Sonntag D, Kohli MR, Setzer FC. A comparison of 2- and 3-dimensional healing assessment after endodontic surgery using cone-beam computed tomographic volumes or periapical radio- graphs. J Endod. 2017;43(7):1072-1079. [CrossRef]
• 24. Ji DX, Ong SH, Foong KW. A level-set based approach for anterior teeth segmentation in cone beam computed tomography images. Comput Biol Med. 2014;50:116-128. [CrossRef]
• 25. Khalil W, EzEldeen M, Van De Casteele E, et al. Validation of cone beam computed tomography-based tooth printing using different three-dimensional printing technologies.Oral Surg Oral Med Oral Pathol Oral Radiol. 2016;121(3):307-315. [CrossRef] 26. Liu Y, Olszewski R, Alexandroni ES, Enciso R, Xu T, Mah JK. The validity of in vivo tooth volume determinations from cone-beam computed tomography. Angle Orthod. 2010;80(1):160-166. [CrossRef]
• 27. Wang Y, He S, Yu L, Li J, Chen S. Accuracy of volumetric measurement of teeth in vivo based on cone beam computer tomography. Orthod Craniofac Res. 2011;14(4):206-212. [CrossRef]
• 28. Wang Y, Liu S ,Wang G, Liu Y. Accurate tooth segmentation with improved hybrid active contour model. Phys Med Biol. 2018;64(1): 015012. [CrossRef]
• 29. Kang HC, Choi C, Shin J, Lee J, Shin YG. Fast and accurate semiau- tomatic segmentation of individual teeth from dental CT images. Comput Math Methods Med. 2015;2015:810796. [CrossRef]
• 30. Shaheen E, Khalil W, Ezeldeen M, et al. Accuracy of segmentation of tooth structures using 3 different CBCT machines. Oral Surg Oral Med Oral Pathol Oral Radiol. 2017;123(1):123-128. [CrossRef]
• 31. Forst D, Nijjar S, Flores-Mir C, Carey J, Secanell M, Lagravere M. Com- parison of in vivo 3D cone-beam computed tomography tooth vol- ume measurement protocols. Prog Orthod. 2014;15(1):69. [CrossRef]
• 32. Rana M, Modrow D, Keuchel J, et al. Development and evaluation of an automatic tumor segmentation tool: A comparison between automatic, semi-automatic and manual segmentation of mandibu- lar odontogenic cysts and tumors. J Craniomaxillofac Surg. 2015; 43(3):355-359. [CrossRef]
• 33. Vallaeys K, Kacem A, Legoux H, Le Tenier M, Hamitouche C, Arbab- Chirani R. 3D dento-maxillary osteolytic lesion and active contour segmentation pilot study in CBCT: Semi-automatic vs manual methods. Dento Maxillo Fac Radiol. 2015;44(8):20150079. [CrossRef]
• 34. Xia Z, Gan Y, Chang L, Xiong J, Zhao Q. Individual tooth segmentation from CT images scanned with contacts of maxillary and mandible teeth. Comput Methods Programs Biomed. 2017;138:1-12. [CrossRef]
• 35. Loubele M, Maes F, Schutyser F, Marchal G, Jacobs R, Suetens P. Assessment of bone segmentation quality of cone-beam CT versus multislice spiral CT: A pilot study. Oral Surg Oral Med Oral Pathol Oral Rad Endod. 2006;102(2):225-234. [CrossRef]
• 36. Michetti J, Georgelin-Gurgel M, Mallet JP, Diemer F, Boulanouar K. Influence of cone beam CT parameters on the output of an auto- matic edge-detection based endodontic segmentation. Dentomax- illofac Radiol. 2015;44(8):20140413.
• 37. Sarikov R, Juodzbalys G. Inferior alveolar nerve injury after mandibu- lar third molar extraction: A literature review. J Oral Maxillofac Res. 2014;5(4):e1. [CrossRef]
• 38. Shavit I, Juodzbalys G. Inferior alveolar nerve injuries following implant placement - importance of early diagnosis and treatment: A systematic review. J Oral Maxillofac Res. 2014;5(4):e2. [CrossRef]
• 39. Sotthivirat S, Narkbuakaew W. Automatic detection of inferior alveolar nerve canals on ct images. Biomedical Circuits and Systems Conference (BioCAS). 2006:142-145. [CrossRef]
• 40. Abdolali F, Zoroofi RA, Abdolali M, Yokota F, Otake Y, Sato Y. Auto- matic segmentation of mandibular canal in cone beam CT images using conditional statistical shape model and fast marching. Int J Comput Assist Radiol Surg. 2017;12(4):581-593. [CrossRef]
• 41. Abdolali F, Zoroofi RA, Otake Y, Sato Y. Automatic segmentation of maxillofacial cysts in cone beam CT images. Comput Biol Med. 2016;72:108-119. [CrossRef]
• 42. Kwak GH, Kwak EJ, Song JM, et al. Automatic mandibular canal detection using a deep convolutional neural network. Sci Rep. 2020;10(1):5711. [CrossRef]
• 43. Shahbazian M, Jacobs R, Wyatt J, et al. Validation of the cone beam computed tomography-based stereolithographic surgical guide aid- ing autotransplantation of teeth: Clinical case-control study. Oral Surg Oral Med Oral Pathol Oral Radiol. 2013;115(5):667-675. [CrossRef]
• 44. Kauke M, Safi AF, Grandoch A, Nickenig HJ, Zöller J, Kreppel M. Image segmentation-based volume approximation-volume as a factor in the clinical management of osteolytic jaw lesions. Dento Maxillo Fac Radiol. 2019;48(1):20180113. [CrossRef]
• 45. Altan Şallı G, Öztürkmen Z. Semi-automated three-dimensional volumetric evaluation of mandibular condyles. Oral Radiol. 2021;37(1): 66-73. [CrossRef] 46. Xi T, Schreurs R, Heerink WJ, Bergé SJ, Maal TJ. A novel region- growing based semi-automatic segmentation protocol for three- dimensional condylar reconstruction using cone beam computed tomography (CBCT). PLoS One. 2014;9(11):e111126. [CrossRef]
• 47. Verhelst PJ, Shaheen E, de Faria Vasconcelos K, et al. Validation of a 3D CBCT-based protocol for the follow-up of mandibular condyle remod- eling. Dento Maxillo Fac Radiol. 2020;49(3):20190364. [CrossRef]
• 48. Nicolielo LFP, Van Dessel J, Shaheen E, et al. Validation of a novel imaging approach using multi-slice CT and cone-beam CT to follow- up on condylar remodeling after bimaxillary surgery. Int J Oral Sci. 2017;9(3):139-144. [CrossRef]
• 49. Kim JJ, Nam H, Kaipatur NR, et al. Reliability and accuracy of seg- mentation of mandibular condyles from different three-dimensional imaging modalities: A systematic review. Dento Maxillo Fac Radiol. 2020;49(5):20190150. [CrossRef]
• 50. Huff TJ, Ludwig PE, Zuniga JM. The potential for machine learning algorithms to improve and reduce the cost of 3-dimensional printing for surgical planning. Expert Rev Med Devices. 2018;15(5):349-356. [CrossRef]
• 51. Bücking TM, Hill ER, Robertson JL, Maneas E, Plumb AA, Nikitichev DI. From medical imaging data to 3D printed anatomical models. PLoS One. 2017;12(5):e0178540. [CrossRef]
• 52. Hodosh M, Povar M, Shklar G. The dental polymer implant concept. J Prosthet Dent. 1969;22(3):371-380. [CrossRef]
• 53. Kohal RJ, Hürzeler MB, Mota LF, Klaus G, Caffesse RG, Strub JR. Cus- tom-made root analogue titanium implants placed into extraction sockets. An experimental study in mon-keys. Clin Oral Implants Res. 1997;8(5):386-392. [CrossRef]
• 54. Pirker W, Kocher A. Root analog zirconia implants: True anatomical design for molar replacement – a case report. Int J Periodontics Restorative Dent. 2011;31(6):663-668.
• 55. Pirker W, Wiedemann D, Lidauer A, Kocher AA. Immediate, single stage, truly anatomic zirconia implant in lower molar replacement: A case report with 2.5 years follow-up. Int J Oral Maxillofac Surg. 2011;40(2):212-216. [CrossRef]
• 56. Regish KM, Sharma D, Prithviraj DR. An overview of immediate root analogue zirconia implants. J Oral Implantol. 2013;39(2):225-233. [CrossRef]
• 57. Mangano FG, De Franco M, Caprioglio A, Macchi A, Piattelli A, Man- gano C. Immediate, non-submerged, root-analogue direct laser metal sintering (DLMS) implants: A 1-year prospective study on 15 patients. Lasers Med Sci. 2014;29(4):1321-1328. [CrossRef]
• 58. Van Assche N, van Steenberghe D, Guerrero ME, et al. Accuracy of implant placement based on pre-surgical planning of three-dimen- sional cone-beam images: A pilot study. J Clin Periodontol. 2007; 34(9):816-821. [CrossRef]
• 59. Loubele M, Guerrero ME, Jacobs R, Suetens P, van Steenberghe D. A comparison of jaw dimensional and quality assessments of bone characteristics with cone-beam CT, spiral tomography, and multi- slice spiral CT. Int J Oral Maxillofac Implants. 2007;22(3):446-454.
• 60. Kim Y, Perinpanayagam H, Lee JK, et al. Comparison of mandibular first molar mesial root canal morphology using micro-computed tomography and clearing technique. Acta Odontol Scand. 2015;73(6): 427-432. [CrossRef]
• 61. Rödig T, Hausdörfer T, Konietschke F, Dullin C, Hahn W, Hülsmann M. Efficacy of D-RaCe and ProTaper Universal retreatment NiTi instru- ments and hand files in removing gutta-percha from curved root canals - a micro-computed tomography study. Int Endod J. 2012; 45(6):580-589. [CrossRef] 62. Marending M, Schicht OO, Paqué F. Initial apical fit of K-files versus LightSpeed LSX instruments assessed by micro-computed tomog- raphy. Int Endod J. 2012;45(2):169-176. [CrossRef]
• 63. Stern S, Patel S, Foschi F, Sherriff M, Mannocci F. Changes in centring and shaping ability using three nickel-titanium instrumentation techniques analysed by micro-computed tomography (μCT). Int Endod J. 2012;45(6):514-523. [CrossRef]
• 64. Lloyd A, Uhles JP, Clement DJ, Garcia-Godoy F. Elimination of intra- canal tissue and debris through a novel laser-activated system assessed using high-resolution micro-computed tomography: A pilot study. J Endod. 2014;40(4):584-587. [CrossRef]
• 65. Versiani MA, Pécora JD, de Sousa-Neto MD. Root and root canal mor- phology of four-rooted maxillary second molars: A micro-computed tomography study. J Endod. 2012;38(7):977-982. [CrossRef]
• 66. Versiani MA, Pécora JD, Sousa-Neto MD. The anatomy of two-rooted mandibular canines determined using micro-computed tomogra- phy. Int Endod J. 2011;44(7):682-687. [CrossRef]
• 67. Michetti J, Basarab A, Diemer F, Kouame D. Comparison of an adap- tive local thresholding method on CBCT and μCT endodontic images. Phys Med Biol. 2017;63(1):015020. [CrossRef]
• 68. Brady E, Mannocci F, Brown J, Wilson R, Patel S. A comparison of cone beam computed tomography and periapical radiography for the detection of vertical root fractures in nonendodontically treated teeth. Int Endod J. 2014;47(8):735-746. [CrossRef]
• 69. Low KM, Dula K, Bürgin W, von Arx T. Comparison of periapical radi- ography and limited cone-beam tomography in posterior maxillary teeth referred for apical surgery. J Endod. 2008;34(5):557-562. [CrossRef]
• 70. Elnagar MH, Aronovich S, Kusnoto B. Digital workflow for combined orthodontics and orthognathic surgery. Oral Maxillofac Surg Clin North Am. 2020;32(1):1-14. [CrossRef]
• 71. Adolphs N, Haberl EJ, Liu W, Keeve E, Menneking H, Hoffmeister B. Virtual planning for craniomaxillofacial surgery – 7 years of experi- ence. J Craniomaxillofac Surg. 2014;42(5):e289-e295. [CrossRef]
• 72. Paniagua B, Cevidanes L, Zhu H, Styner M. Outcome quantification using SPHARM-PDM toolbox in orthognathic surgery. Int J Comput Assist Radiol Surg. 2011;6(5):617-626. [CrossRef]
• 73. Manhaes-Caldas D, Oliveira ML, Groppo FC, Haiter-Neto F. Volumet- ric assessment of the dental crown for sex estimation by means of cone-beam computed tomography. Forensic Sci Int. 2019;303: 109920. [CrossRef]
• 74. Haghanifar S, Ghobadi F, Vahdani N, Bijani A. Age estimation by pulp/ tooth area ratio in anterior teeth using cone-beam computed tomography: Comparison of four teeth. J Appl Oral Sci. 2019;27: e20180722. [CrossRef]
• 75. Merdietio Boedi R, Banar N, De Tobel J, Bertels J, Vandermeulen D, Thevissen PW. Effect of lower third molar segmentations on auto- mated tooth development staging using a convolutional neural net- work. J Forensic Sci. 2020;65(2):481-486. [CrossRef]
• 76. Li H, Zhang Z, Liu Z. Application of artificial neural networks for catal- ysis: A review. Catalysts. 2017;7(10):306. [CrossRef]
• 77. Kandel I, Castelli M. How deeply to fine-tune a convolutional neural network: A case study using a histopathology dataset. Appl Sci. 2020;10(10):3359. [CrossRef]