Deep-learning approach for caries detection and segmentation on dental bitewing radiographs

Basit Öğe Kaydı
dc.authoridBAYRAKDAR, Ibrahim Sevki/0000-0001-5036-9867
dc.authoridYasa, Yasin/0000-0002-4388-2125
dc.authoridBilgir, Elif/0000-0001-9521-4682
dc.authoridAtasoy, Samet/0000-0002-7439-1046
dc.authoridSAGLAM, HACI/0000-0002-6598-8262
dc.authoridKazan, Hande/0000-0001-7792-5106
dc.authoridOrhan, Kaan/0000-0001-6768-0176
dc.contributor.authorBayrakdar, Ibrahim Sevki
dc.contributor.authorOrhan, Kaan
dc.contributor.authorAkarsu, Serdar
dc.contributor.authorCelik, Ozer
dc.contributor.authorAtasoy, Samet
dc.contributor.authorPekince, Adem
dc.contributor.authorYasa, Yasin
dc.date.accessioned2024-09-29T15:51:26Z
dc.date.available2024-09-29T15:51:26Z
dc.date.issued2022
dc.departmentKarabük Üniversitesien_US
dc.description.abstractObjectives The aim of this study is to recommend an automatic caries detection and segmentation model based on the Convolutional Neural Network (CNN) algorithms in dental bitewing radiographs using VGG-16 and U-Net architecture and evaluate the clinical performance of the model comparing to human observer. Methods A total of 621 anonymized bitewing radiographs were used to progress the Artificial Intelligence (AI) system (CranioCatch, Eskisehir, Turkey) for the detection and segmentation of caries lesions. The radiographs were obtained from the Radiology Archive of the Department of Oral and Maxillofacial Radiology of the Faculty of Dentistry of Ordu University. VGG-16 and U-Net implemented with PyTorch models were used for the detection and segmentation of caries lesions, respectively. Results The sensitivity, precision, and F-measure rates for caries detection and caries segmentation were 0.84, 0.81; 0.84, 0.86; and 0.84, 0.84, respectively. Comparing to 5 different experienced observers and AI models on external radiographic dataset, AI models showed superiority to assistant specialists. Conclusion CNN-based AI algorithms can have the potential to detect and segmentation of dental caries accurately and effectively in bitewing radiographs. AI algorithms based on the deep-learning method have the potential to assist clinicians in routine clinical practice for quickly and reliably detecting the tooth caries. The use of these algorithms in clinical practice can provide to important benefit to physicians as a clinical decision support system in dentistry.en_US
dc.description.sponsorshipEskisehir Osmangazi University Scientific Research Projects Coordination Unit [202045E06]en_US
dc.description.sponsorshipThis work has been supported by Eskisehir Osmangazi University Scientific Research Projects Coordination Unit under Grant number 202045E06.en_US
dc.identifier.doi10.1007/s11282-021-00577-9
dc.identifier.endpage479en_US
dc.identifier.issn0911-6028
dc.identifier.issn1613-9674
dc.identifier.issue4en_US
dc.identifier.pmid34807344en_US
dc.identifier.scopus2-s2.0-85119662114en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.startpage468en_US
dc.identifier.urihttps://doi.org/10.1007/s11282-021-00577-9
dc.identifier.urihttps://hdl.handle.net/20.500.14619/4074
dc.identifier.volume38en_US
dc.identifier.wosWOS:000721401600001en_US
dc.identifier.wosqualityQ4en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.indekslendigikaynakPubMeden_US
dc.language.isoenen_US
dc.publisherSpringeren_US
dc.relation.ispartofOral Radiologyen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectArtificial intelligenceen_US
dc.subjectDeep learningen_US
dc.subjectTooth cariesen_US
dc.subjectBitewing radiographsen_US
dc.subjectDentistryen_US
dc.titleDeep-learning approach for caries detection and segmentation on dental bitewing radiographsen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
PubMed İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu