The diagnostic performance of impacted third molars in the mandible: A review of deep learning on panoramic radiographs

Background: Mandibular third molar is prone to impaction, resulting in its inability to erupt into the oral cavity. The radiographic examination is required to support the odontectomy of impacted teeth. The use of computer-aided diagnosis based on deep learning is emerging in the field of medical an...

Full description

Saved in:
Bibliographic Details
Main Authors: Amalia Nur Faadiya, Rini Widyaningrum, Pingky Krisna Arindra, Silviana Farrah Diba
Format: Article
Language:English
Published: Springer 2024-03-01
Series:Saudi Dental Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1013905223002493
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850037755902427136
author Amalia Nur Faadiya
Rini Widyaningrum
Pingky Krisna Arindra
Silviana Farrah Diba
author_facet Amalia Nur Faadiya
Rini Widyaningrum
Pingky Krisna Arindra
Silviana Farrah Diba
author_sort Amalia Nur Faadiya
collection DOAJ
description Background: Mandibular third molar is prone to impaction, resulting in its inability to erupt into the oral cavity. The radiographic examination is required to support the odontectomy of impacted teeth. The use of computer-aided diagnosis based on deep learning is emerging in the field of medical and dentistry with the advancement of artificial intelligence (AI) technology. This review describes the performance and prospects of deep learning for the detection, classification, and evaluation of third molar-mandibular canal relationships on panoramic radiographs. Methods: This work was conducted using three databases: PubMed, Google Scholar, and Science Direct. Following the literature selection, 49 articles were reviewed, with the 12 main articles discussed in this review. Results: Several models of deep learning are currently used for segmentation and classification of third molar impaction with or without the combination of other techniques. Deep learning has demonstrated significant diagnostic performance in identifying mandibular impacted third molars (ITM) on panoramic radiographs, with an accuracy range of 78.91% to 90.23%. Meanwhile, the accuracy of deep learning in determining the relationship between ITM and the mandibular canal (MC) ranges from 72.32% to 99%. Conclusion: Deep learning-based AI with high performance for the detection, classification, and evaluation of the relationship of ITM to the MC using panoramic radiographs has been developed over the past decade. However, deep learning must be improved using large datasets, and the evaluation of diagnostic performance for deep learning models should be aligned with medical diagnostic test protocols. Future studies involving collaboration among oral radiologists, clinicians, and computer scientists are required to identify appropriate AI development models that are accurate, efficient, and applicable to clinical services.
format Article
id doaj-art-5f609ad6a1f84ca1ae72e46adc2ea878
institution DOAJ
issn 1013-9052
language English
publishDate 2024-03-01
publisher Springer
record_format Article
series Saudi Dental Journal
spelling doaj-art-5f609ad6a1f84ca1ae72e46adc2ea8782025-08-20T02:56:47ZengSpringerSaudi Dental Journal1013-90522024-03-0136340441210.1016/j.sdentj.2023.11.025The diagnostic performance of impacted third molars in the mandible: A review of deep learning on panoramic radiographsAmalia Nur Faadiya0Rini Widyaningrum1Pingky Krisna Arindra2Silviana Farrah Diba3Dental Medicine Study Program, Faculty of Dentistry, Universitas Gadjah Mada, Yogyakarta, IndonesiaDepartment of Dentomaxillofacial Radiology, Faculty of Dentistry, Universitas Gadjah Mada, Yogyakarta, Indonesia; Corresponding author at: Department of Dentomaxillofacial Radiology, Faculty of Dentistry, Universitas Gadjah Mada, Denta Street, No. 1, Sleman Regency, Yogyakarta, Indonesia.Department of Oral and Maxillofacial Surgery, Faculty of Dentistry, Universitas Gadjah Mada, Yogyakarta, IndonesiaDepartment of Dentomaxillofacial Radiology, Faculty of Dentistry, Universitas Gadjah Mada, Yogyakarta, IndonesiaBackground: Mandibular third molar is prone to impaction, resulting in its inability to erupt into the oral cavity. The radiographic examination is required to support the odontectomy of impacted teeth. The use of computer-aided diagnosis based on deep learning is emerging in the field of medical and dentistry with the advancement of artificial intelligence (AI) technology. This review describes the performance and prospects of deep learning for the detection, classification, and evaluation of third molar-mandibular canal relationships on panoramic radiographs. Methods: This work was conducted using three databases: PubMed, Google Scholar, and Science Direct. Following the literature selection, 49 articles were reviewed, with the 12 main articles discussed in this review. Results: Several models of deep learning are currently used for segmentation and classification of third molar impaction with or without the combination of other techniques. Deep learning has demonstrated significant diagnostic performance in identifying mandibular impacted third molars (ITM) on panoramic radiographs, with an accuracy range of 78.91% to 90.23%. Meanwhile, the accuracy of deep learning in determining the relationship between ITM and the mandibular canal (MC) ranges from 72.32% to 99%. Conclusion: Deep learning-based AI with high performance for the detection, classification, and evaluation of the relationship of ITM to the MC using panoramic radiographs has been developed over the past decade. However, deep learning must be improved using large datasets, and the evaluation of diagnostic performance for deep learning models should be aligned with medical diagnostic test protocols. Future studies involving collaboration among oral radiologists, clinicians, and computer scientists are required to identify appropriate AI development models that are accurate, efficient, and applicable to clinical services.http://www.sciencedirect.com/science/article/pii/S1013905223002493Mandibular canalRadiographPanoramicDeep learningThird molarImpacted
spellingShingle Amalia Nur Faadiya
Rini Widyaningrum
Pingky Krisna Arindra
Silviana Farrah Diba
The diagnostic performance of impacted third molars in the mandible: A review of deep learning on panoramic radiographs
Saudi Dental Journal
Mandibular canal
Radiograph
Panoramic
Deep learning
Third molar
Impacted
title The diagnostic performance of impacted third molars in the mandible: A review of deep learning on panoramic radiographs
title_full The diagnostic performance of impacted third molars in the mandible: A review of deep learning on panoramic radiographs
title_fullStr The diagnostic performance of impacted third molars in the mandible: A review of deep learning on panoramic radiographs
title_full_unstemmed The diagnostic performance of impacted third molars in the mandible: A review of deep learning on panoramic radiographs
title_short The diagnostic performance of impacted third molars in the mandible: A review of deep learning on panoramic radiographs
title_sort diagnostic performance of impacted third molars in the mandible a review of deep learning on panoramic radiographs
topic Mandibular canal
Radiograph
Panoramic
Deep learning
Third molar
Impacted
url http://www.sciencedirect.com/science/article/pii/S1013905223002493
work_keys_str_mv AT amalianurfaadiya thediagnosticperformanceofimpactedthirdmolarsinthemandibleareviewofdeeplearningonpanoramicradiographs
AT riniwidyaningrum thediagnosticperformanceofimpactedthirdmolarsinthemandibleareviewofdeeplearningonpanoramicradiographs
AT pingkykrisnaarindra thediagnosticperformanceofimpactedthirdmolarsinthemandibleareviewofdeeplearningonpanoramicradiographs
AT silvianafarrahdiba thediagnosticperformanceofimpactedthirdmolarsinthemandibleareviewofdeeplearningonpanoramicradiographs
AT amalianurfaadiya diagnosticperformanceofimpactedthirdmolarsinthemandibleareviewofdeeplearningonpanoramicradiographs
AT riniwidyaningrum diagnosticperformanceofimpactedthirdmolarsinthemandibleareviewofdeeplearningonpanoramicradiographs
AT pingkykrisnaarindra diagnosticperformanceofimpactedthirdmolarsinthemandibleareviewofdeeplearningonpanoramicradiographs
AT silvianafarrahdiba diagnosticperformanceofimpactedthirdmolarsinthemandibleareviewofdeeplearningonpanoramicradiographs