Article Data

  • Views 620
  • Dowloads 176

Original Research

Open Access

Classification of presence of missing teeth in each quadrant using deep learning artificial intelligence on panoramic radiographs of pediatric patients

  • Eunjin Kim1,†
  • Jae Joon Hwang2,3,†
  • Bong-Hae Cho2,3
  • Eungyung Lee1,3
  • Jonghyun Shin1,3,*,

1Department of Pediatric Dentistry, School of Dentistry, Pusan National University, 50612 Yangsan, Republic of Korea

2Department of Oral and Maxillofacial Radiology, School of Dentistry, Pusan National University, 50612 Yangsan, Republic of Korea

3Dental and Life Science Institute & Dental Research Institute, School of Dentistry, Pusan National University, 50612 Yangsan, Republic of Korea

DOI: 10.22514/jocpd.2024.062 Vol.48,Issue 3,May 2024 pp.76-85

Submitted: 24 August 2023 Accepted: 21 September 2023

Published: 03 May 2024

*Corresponding Author(s): Jonghyun Shin E-mail: jonghyuns@pusan.ac.kr

† These authors contributed equally.

Abstract

Early tooth loss in pediatric patients can lead to various complications, making quick and accurate diagnosis essential. This study aimed to develop a novel deep learning model for classification of missing teeth on panoramic radiographs in pediatric patients and to assess the accuracy. The study included patients aged 8–16 years who visited the Pusan National University Dental Hospital and underwent panoramic radiography. A total of 806 panoramic radiographs were retrospectively analyzed to determine the presence or absence of missing teeth for each tooth number. Moreover, each panoramic radiograph was divided into four quadrants, each of a smaller size, containing both primary and permanent teeth, generating 3224 data. Quadrants with missing teeth (n = 1457) were set as the experimental group, and quadrants without missing teeth (n = 1767) were set as the control group. The data were split into training and validation sets in a 4:1 ratio, and a 5-fold cross-validation was conducted. A gradient-weighted class activation map was used to visualize the deep learning model. The average values of sensitivity, specificity, accuracy, precision, recall and F1-score of this deep learning model were 0.635, 0.814, 0.738, 0.730, 0.732 and 0.731, respectively. In the experimental group, the accuracy was the highest for missing canines and premolars, and the lowest for molars. The deep learning model exhibited a moderate to good distinguishing power with a classification performance of 0.730. This deep learning model and the newly defined small sized region of interest proved adequate for classifying the presence of missing teeth.


Keywords

Missing teeth; Deep learning; Region of interest; Pediatric and adolescent; Panorama


Cite and Share

Eunjin Kim,Jae Joon Hwang,Bong-Hae Cho,Eungyung Lee,Jonghyun Shin. Classification of presence of missing teeth in each quadrant using deep learning artificial intelligence on panoramic radiographs of pediatric patients. Journal of Clinical Pediatric Dentistry. 2024. 48(3);76-85.

References

[1] Kim E, Park S, Lee E, Jeong T, Shin J. Prevalence and patterns of congenitally missing teeth among pediatric patients aged 8–16 in Pusan national university dental hospital. Journal of the Korean Academy of Pediatric Dentistry. 2023; 50: 179–191.

[2] Rakhshan V. Congenitally missing teeth (hypodontia): a review of the literature concerning the etiology, prevalence, risk factors, patterns and treatment. Dental Research Journal. 2015; 12: 1–13.

[3] Ahamed SS, Reddy V, Krishnakumar R, Mohan M, Sugumaran D, Rao A. Prevalence of early loss of primary teeth in 5–10-year-old school children in Chidambaram town. Contemporary Clinical Dentistry. 2012; 3: 27–30.

[4] Na C, Kim J. A study of congenitally missing permanent teeth in Wonju Severance Christian Hospital. Journal of the Korean Academy of Pediatric Dentistry. 2023; 50: 35–46.

[5] Arai K. Tooth agenesis patterns in Japanese orthodontic patients with nonsyndromic oligodontia. American Journal of Orthodontics and Dentofacial Orthopedics. 2019; 156: 238–247.

[6] American Dental Association Council on Scientific Affairs. The use of dental radiographs: update and recommendations. The Journal of the American Dental Association. 2006; 137: 1304–1312.

[7] Peretz B, Gotler M, Kaffe I. Common errors in digital panoramic radiographs of patients with mixed dentition and patients with permanent dentition. International Journal of Dentistry. 2012; 2012: 1–7.

[8] Barrett AP, Waters BE, Griffiths CJ. A critical evaluation of panoramic radiography as a screening procedure in dental practice. Oral Surgery, Oral Medicine, Oral Pathology. 1984; 57: 673–677.

[9] Ignelzi Jr MA, Fields HW, Vann Jr WF. Screening panoramic radiographs in children: prevalence data and implications. Pediatric Dentistry. 1989; 11: 279–285.

[10] Kim J, Hwang JJ, Jeong T, Cho B, Shin J. Deep learning-based identification of mesiodens using automatic maxillary anterior region estimation in panoramic radiography of children. Dentomaxillofacial Radiology. 2022; 51: 20210528.

[11] Kong Z, Xiong F, Zhang C, Fu Z, Zhang M, Weng J, et al. Automated maxillofacial segmentation in panoramic dental X-ray images using an efficient encoder-decoder network. IEEE Access. 2020; 8: 207822–207833.

[12] Erickson BJ, Korfiatis P, Akkus Z, Kline TL. Machine learning for medical imaging. Radiographics. 2017; 37: 505–515.

[13] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015; 521: 436–444.

[14] Hwang J, Jung Y, Cho B, Heo M. An overview of deep learning in the field of dentistry. Imaging Science in Dentistry. 2019; 49: 1–7.

[15] Seo HJ, Hwang JJ, Jeong TS, Shin JH. Comparison of deep learning models for cervical vertebral maturation stage classification on lateral cephalometric radiographs. Journal of Clinical Medicine. 2021; 10: 3591.

[16] Ghorbanzadeh O, Blaschke T, Gholamnia K, Meena SR, Tiede D, Aryal J. Evaluation of different machine learning methods and deep-learning convolutional neural networks for landslide detection. Remote Sensing. 2019; 11: 196.

[17] Kohli M, Prevedello LM, Filice RW, Geis JR. Implementing machine learning in radiology practice and research. American Journal of Roentgenology. 2017; 208: 754–760.

[18] Hung K, Montalvao C, Tanaka R, Kawai T, Bornstein MM. The use and performance of artificial intelligence applications in dental and maxillofacial radiology: a systematic review. Dentomaxillofacial Radiology. 2020; 49: 20190107.

[19] Hoang TM, Nam SH, Park KR. Enhanced detection and recognition of road markings based on adaptive region of interest and deep learning. IEEE Access. 2019; 7: 109817–109832.

[20] Ahn YH, Hwang JJ, Jung Y-H, Jeong TS, Shin JH. Automated mesiodens classification system using deep learning on panoramic radiographs of children. Diagnostics. 2021; 11: 1477.

[21] Kuwada C, Ariji Y, Fukuda M, Kise Y, Fujita H, Katsumata A, et al. Deep learning systems for detecting and classifying the presence of impacted supernumerary teeth in the maxillary incisor region on panoramic radiographs. Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology. 2020; 130: 464–469.

[22] Park JM, Lee JS, Moon SG, Lee KB. Deep learning based detection of missing tooth regions for dental implant planning in panoramic radiographic images. Applied Sciences. 2022; 12: 1595.

[23] Kim J, Seo H, Park S, Lee E, Jeong T, Nam OH, et al. Utilization of an artificial intelligence program using the Greulich-Pyle method to evaluate bone age in the skeletal maturation stage. Journal of the Korean Academy of Pediatric Dentistry. 2023; 50: 89–103.

[24] Al-Sarem M, Al-Asali M, Alqutaibi AY, Saeed F. Enhanced tooth region detection using pretrained deep learning models. International Journal of Environmental Research and Public Health. 2022; 19: 15414.

[25] Chandrashekar G, AlQarni S, Bumann EE, Lee Y. Collaborative deep learning model for tooth segmentation and identification using panoramic radiographs. Computers in Biology and Medicine. 2022; 148: 105829.

[26] Biggerstaff RH, Phillips JR. A quantitative comparison of paralleling long-cone and bisection-of-angle periapical radiography. Oral Surgery, Oral Medicine, Oral Pathology. 1976; 41: 673–677.

[27] de Marsillac MdWS, Andrade MRT, de Oliveira Fonseca R, Marcal SLM, Santos VLC. Dental anomalies in panoramic radiographs of pediatric patients. General Dentistry. 2013; 61: e29–e33.

[28] Kaya E, Gunec HG, Aydin KC, Urkmez ES, Duranay R, Ates HF. A deep learning approach to permanent tooth germ detection on pediatric panoramic radiographs. Imaging Science in Dentistry. 2022; 52: 275–281.

[29] Sukegawa S, Yoshii K, Hara T, Yamashita K, Nakano K, Yamamoto N, et al. Deep neural networks for dental implant system classification. Biomolecules. 2020; 10: 984.

[30] Endres MG, Hillen F, Salloumis M, Sedaghat AR, Niehues SM, Quatela O, et al. Development of a deep learning algorithm for periapical disease detection in dental radiographs. Diagnostics. 2020; 10: 430.

[31] Lee JH, Kim DH, Jeong SN, Choi SH. Diagnosis and prediction of periodontally compromised teeth using a deep learning-based convolutional neural network algorithm. Journal of Periodontal & Implant Science. 2018; 48: 114–123.

[32] Abdi AH, Kasaei S, Mehdizadeh M. Automatic segmentation of mandible in panoramic x-ray. Journal of Medical Imaging. 2015; 2: 044003.

[33] Vinayahalingam S, Kempers S, Limon L, Deibel D, Maal T, Hanisch M, et al. Classification of caries in third molars on panoramic radiographs using deep learning. Scientific Reports. 2021: 11: 12609.

[34] Dibeh G, Hilal A, Charara J. A novel approach for dental panoramic radiograph segmentation. 2018 IEEE International Multidisciplinary Conference on Engineering Technology (IMCET). 2018; 19: 1–6.

[35] Fukuda M, Ariji Y, Kise Y, Nozawa M, Kuwada C, Funakoshi T, et al. Comparison of 3 deep learning neural networks for classifying the relationship between the mandibular third molar and the mandibular canal on panoramic radiographs. Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology. 2020; 130: 336–343.

[36] Estai M, Tennant M, Gebauer D, Brostek A, Vignarajan J, Mehdizadeh M, et al. Deep learning for automated detection and numbering of permanent teeth on panoramic images. Dentomaxillofacial Radiology. 2022; 51: 20210296.

[37] Heuberer S, Ulm C, Zechner W, Laky B, Watzak G. Patterns of congenitally missing teeth of non-syndromic and syndromic patients treated at a single-center over the past thirty years. Archives of Oral Biology. 2019; 98: 140–147.

[38] Narkhede S. Understanding auc-roc curve. Towards Data Science. 2018; 26: 220–227.

[39] Duan J, Wang X, Chi J, Chen H, Bai L, Hu Q, et al. Correlation between the variables collected at admission and progression to severe cases during hospitalization among patients with COVID-19 in Chongqing. Journal of Medical Virology. 2020; 92: 2616–2622.

[40] Liao H, Long Y, Han R, Wang W, Xu L, Liao M, et al. Deep learning-based classification and mutation prediction from histopathological images of hepatocellular carcinoma. Clinical and Translational Medicine. 2020; 10: e102.

[41] Cao W, An X, Cong L, Lyu C, Zhou Q, Guo R. Application of deep learning in quantitative analysis of 2-dimensional ultrasound imaging of nonalcoholic fatty liver disease. Journal of Ultrasound in Medicine. 2020; 39: 51–59.

[42] Stewart AX, Nuthmann A, Sanguinetti G. Single-trial classification of EEG in a visual object task using ICA and machine learning. Journal of Neuroscience Methods. 2014; 228: 1–14.


Abstracted / indexed in

Science Citation Index Expanded (SciSearch) Created as SCI in 1964, Science Citation Index Expanded now indexes over 9,500 of the world’s most impactful journals across 178 scientific disciplines. More than 53 million records and 1.18 billion cited references date back from 1900 to present.

Biological Abstracts Easily discover critical journal coverage of the life sciences with Biological Abstracts, produced by the Web of Science Group, with topics ranging from botany to microbiology to pharmacology. Including BIOSIS indexing and MeSH terms, specialized indexing in Biological Abstracts helps you to discover more accurate, context-sensitive results.

Google Scholar Google Scholar is a freely accessible web search engine that indexes the full text or metadata of scholarly literature across an array of publishing formats and disciplines.

JournalSeek Genamics JournalSeek is the largest completely categorized database of freely available journal information available on the internet. The database presently contains 39226 titles. Journal information includes the description (aims and scope), journal abbreviation, journal homepage link, subject category and ISSN.

Current Contents - Clinical Medicine Current Contents - Clinical Medicine provides easy access to complete tables of contents, abstracts, bibliographic information and all other significant items in recently published issues from over 1,000 leading journals in clinical medicine.

BIOSIS Previews BIOSIS Previews is an English-language, bibliographic database service, with abstracts and citation indexing. It is part of Clarivate Analytics Web of Science suite. BIOSIS Previews indexes data from 1926 to the present.

Journal Citation Reports/Science Edition Journal Citation Reports/Science Edition aims to evaluate a journal’s value from multiple perspectives including the journal impact factor, descriptive data about a journal’s open access content as well as contributing authors, and provide readers a transparent and publisher-neutral data & statistics information about the journal.

Scopus: CiteScore 2.0 (2022) Scopus is Elsevier's abstract and citation database launched in 2004. Scopus covers nearly 36,377 titles (22,794 active titles and 13,583 Inactive titles) from approximately 11,678 publishers, of which 34,346 are peer-reviewed journals in top-level subject fields: life sciences, social sciences, physical sciences and health sciences.

Submission Turnaround Time

Conferences

Top