Ortodontide Yapay Zeka Uygulamaları
Özet
Yapay zeka teknolojisi, veri işleme kabiliyeti sayesinde tıp ve diş hekimliğinde maliyetleri, tedavi sürelerini ve tıbbi hataları azaltarak önemli bir değişim yaratmaktadır. Ortodonti alanında ise hasta iletişiminden tanı ve tedavi süreçlerine kadar geniş bir yelpazede yenilikçi çözümler sunmaktadır. Bu kapsamda sefalometrik analiz noktalarının belirlenmesinde derin öğrenme algoritmaları, manuel ölçümlere kıyasla yüksek doğruluk oranıyla süreci hızlandırmaktadır. İskeletsel maturasyon ve kemik yaşı tahmininde yapay sinir ağları, el-bilek ve lateral sefalometrik radyografileri uzman radyologlar kadar başarılı şekilde analiz edebilmektedir. Kritik bir aşama olan diş çekimli veya çekimsiz tedavi kararında, yapay zeka modelleri vaka parametrelerini değerlendirerek %80 ila %94 arasında yüksek bir başarıyla klinisyenlere rehberlik etmektedir. Benzer şekilde, iskeletsel bozuklukların düzeltilmesine yönelik ortognatik cerrahi endikasyonlarının ayırıcı tanısında derin evrişimli sinir ağları %96'ya varan doğruluk performansı sergilemektedir. Son olarak, estetik ve objektif yüz oranlarının değerlendirilmesinde insan algısını taklit eden yapay zeka, cerrahi operasyonların yüz çekiciliği ve genç görünüm üzerindeki etkilerini nesnel ve tekrarlanabilir bir şekilde ölçebilmektedir. Sonuç olarak yapay zeka, ortodonti uzmanlarının iş yükünü azaltan ve teşhiste güvenilir bir ikinci görüş sağlayan etkili bir destek aracı haline gelmiştir.
Artificial intelligence technology creates a significant transformation in medicine and dentistry by reducing costs, treatment periods, and medical errors thanks to its data processing capability. In the field of orthodontics, it offers innovative solutions in a wide range from patient communication to diagnosis and treatment processes. In this context, deep learning algorithms in determining cephalometric analysis landmarks accelerate the process with high accuracy compared to manual measurements. In predicting skeletal maturation and bone age, artificial neural networks can analyze hand-wrist and lateral cephalometric radiographs as successfully as expert radiologists. In the critical phase of extraction or non-extraction treatment decisions, AI models guide clinicians with a high success rate between 80% and 94% by evaluating case parameters. Similarly, deep convolutional neural networks exhibit an accuracy performance of up to 96% in the differential diagnosis of orthognathic surgery indications for correcting skeletal disorders. Finally, in evaluating aesthetic and objective facial proportions, AI mimicking human perception can objectively and repeatably measure the effects of surgical operations on facial attractiveness and youthful appearance. Consequently, artificial intelligence has become an effective decision-support tool that reduces the workload of orthodontists and provides a reliable second opinion in diagnosis.
Referanslar
Russell S, Norvig P. (2010). Artificial Intelligence A Modern Approach. (3rd ed.). New Jersey: Pearson Education.
Wong S, Al-Hasani H, Alam Z, Alam A. Artificial intelligence in radiology: how will we be affected? European Radiology, 2019; 29(1), 141-143.
Akdeniz BS, Tosun ME. A review of the use of artificial intelligence in orthodontics. Journal of Experimental and Clinical Medicine, 2021; 38(2), 157-162.
Shan T, Tay F, Gu L. Application of artificial intelligence in dentistry. Journal of Dental Research, 2021; 100(3), 232-244.
Nilsson NJ, Nilsson NJ. (1998). Artificial intelligence: A new synthesis. (1st ed.). Morgan Kaufmann Publishers.
Faber J, Faber C, Faber P. Artificial intelligence in orthodontics. Journal of the Asian Pacific Orthodontic Society, 2016; 9, 201-205.
Yılmaz A. 2020. Yapay zeka nedir? Aksan G, (Ed.), Yapay Zeka (1-22). İstanbul: KODLAB.
Küçük EB, Akdoğan EG. (2021). Up-to-Date Artificial Intelligence In Orthodontics. Cem Evereklioğlu (Ed.), Research & Reviews in Health Sciences-II, (69-92). Ankara: Gece Publishing.
Kattadiyil MT, Mursic Z, AlRumaih H, Goodacre CJ. Intraoral scanning of hard and soft tissues for partial removable dental prosthesis fabrication. Journal of Prosthetic Dentistry, 2014; 112, 444-448.
Miller R, Dijkman D, Riolo M, Moyers R. Graphic computerization of cephalometric data. Journal of Dental Research, 1971; (50)5, 1363.
Hutton TJ, Cunningham S, Hammond P. An evaluation of active shape models for the automatic identification of cephalometric landmarks. European Journal Orthodontics, 2000; 22(5), 499-508.
Park J, Hwang H, Moon J, Yu Y, Kim H, Her S. Automated identification of cephalometric landmarks: part 1-comparisons between the latest deep-learning methods YOLOV3 and SSD. Angle Orthodontist, 2019; 89(6), 903-909.
Montúfar J, Romero M, Scougall-Vilchis RJ. Automatic 3-dimensional cephalometric landmarking based on active shape models in related projections. American Journal of Orthodontics and Dentofacial Orthopedics, 2018; 153, 449-458.
Montúfar J, Romero M, Scougall-Vilchis RJ. Hybrid approach for automatic cephalometric landmark annotation on cone-beam computed tomography volumes. American Journal of Orthodontics and Dentofacial Orthopedics, 2018; 154, 140-150.
Kunz F, Stellzig-Eisenhauer A, Zeman F, Boldt J. Artificial intelligence in orthodontics: Evaluation of a fully automated cephalometric analysis using a customized convolutional neural network. Journal of Orofacial Orthopedics, 2020; 81, 52-68.
Cohen AM, Ip HH, Linney AD. A preliminary study of computer recognition and identification of skeletal landmarks as a new method of cephalometric analysis. British Journal of Orthodontics, 1984; 11(3), 143–154.
Rueda S, Alcañiz M. An approach for the automatic cephalometric landmark detection using mathematical morphology and active appearance models. Medical Image Computing and Computer-Assisted Intervention: MICCAI International Conference on Medical Image Computing and Computer-Assisted Intervention, 2006; 9(1), 159-166.
Rudolph DJ, Sinclair PM, Coggins JM. Automatic computerized radiographic identification of cephalometric landmarks. American Journal of Orthodontics and Dentofacial Orthopedics, 1998; 113(2), 173-179.
Hwang HW, Moon JH, Kim MG, Donatelli RE, Lee SJ. Evaluation of automated cephalometric analysis based on the latest deep learning method. The Angle Orthodontist, 2021; 91(3), 329-335.
Lee SM, Kim HP, Jeon K, Lee SH, Seo JK. Automatic 3D cephalometric annotation system using shadowed 2D image-based machine learning. Physics in Medicine and Biology, 2019; 64(5).
Baccetti T, Franchi L, McNamara JAJ. An improved version of the cervical vertebral maturation (CVM) method for the assessment of mandibular growth. The Angle Orthodontist, 2002; 72(4), 316–323.
Franchi L, Baccetti T, De Toffol L, Polimeni A, Cozza P. Phases of the dentition for the assessment of skeletal maturity: a diagnostic performance study. American Journal of Orthodontics and Dentofacial Orthopedics, 2008; 133(3), 392-395.
Lee H, Tajmir S, Lee J, Zissen M, Yeshiwas BA, Alkasab TK, Choy G, Do S. Fully automated deep learning system for bone age assessment. Journal of Digital Imaging, 2017; 30(4), 427-441.
Larson DB, Chen MC, Lungren MP, Halabi SS, Stence NV, Langlotz CP. Performance of a deep-learning neural network model in assessing skeletal maturity on pediatric hand radiographs. Radiology. 2018; 287(1), 313-322.
Çelik H, İçer S. Çocuklarda Yaş Tayini İçin Yapay Sinir Ağlarının Kullanıldığı Yeni Bir Yöntem. 24th Signal Processing and Communication application Conference (SIU), 2016; 1189-1192.
Kök H, Acilar AM, İzgi MS. Usage and comparison of artificial intelligence algorithms for determination of growth and development by cervical vertebrae stages in orthodontics. Progress in Orthodontics, 2019; 20(1), 41.
Amasya H, Cesur E, Yıldırım D, Orhan K. Validation of cervical vertebral maturation stages: Artificial intelligence vs human observer visual analysis. American Journal of Orthodontics and Dentofacial Orthopedics, 2020; 158(6), 173-179.
Xie X, Wang L, Wang A. Artificial neural network modeling for deciding if extractions are necessary prior to orthodontic treatment. The Angle Orthodontist, 2010; 80(2), 262–266.
Jung SK, Kim TW. New approach for the diagnosis of extractions with neural network machine learning. American Journal of Orthodontics and Dentofacial Orthopedics, 2016; 149(1), 127-133.
Li P, Kong D, Tang T, Su D, Yang P, Wang H. Orthodontic treatment planning based on artificial neural networks. Scientific Reports, 2019; 9, 2037.
Choi, HI, Jung SK, Baek SH, Lim WH, Ahn SJ, Yang IH, Kim TW. Artificial Intelligent Model With Neural Network Machine Learning for the Diagnosis of Orthognathic Surgery. The Journal of Craniofacial Surgery, 2019; 30(7), 1986-1989.
Lee KS, Ryu JJ, Jang HS, Lee DY, Jung SK. Deep Convolutional Neural Networks Based Analysis of Cephalometric Radiographs for Differential Diagnosis of Orthognathic Surgery Indications. Applied Sciences, 2020; 10(6), 2124.
Knight H, Keith O. Ranking facial attractiveness. European Journal Orthodontics, 2005; 27, 340-348.
Yu X, Liu B, Pei Y, Xu T. Evaluation of facial attractiveness for patients with malocclusion: A machine-learning technique employing Procrustes. Angle Orthodontics, 2014; 84, 410-416.
Patcas R, Bernini DAJ, Volokitin A, Agustsson E, Rothe R, Timofte R. Applying artificial intelligence to assess the impact of orthognathic treatment on facial attractiveness and estimated age. International Journal of Oral Maxillofacial Surgery, 2019; 48, 77-83.
Murata S, Lee C, Tanikawa C, Date S. Towards a Fully Automated Diagnostic System for Orthodontic Treatment in Dentistry. 2017 IEEE 13th International Conference on e-Science (e-Science), 2017; 1-8.
Soğancı B, Tağrikulu B. (2021). Yapay zekânın ortodontideki kullanım alanları ve güncel yaklaşımlar. Cura N, (Ed.), Pandemi Sürecinde Ortodonti: “Dijital Ortodonti” ve “Tele Ortodonti” (66-74). Ankara: Türkiye Klinikleri.
