Comparative evaluation of deep learning models for the classification of impacted maxillary canines on panoramic radiographs

Basit Öğe Kaydı
dc.authorid0000-0001-9840-4211
dc.authorid0009-0004-6316-6072
dc.authorid0009-0008-8331-9493
dc.authorid0000-0001-7859-2198
dc.authorid0000-0003-4966-9779
dc.authorid0000-0003-2460-0724
dc.contributor.authorTokatlı, Nazlı
dc.contributor.authorErdem, Buket
dc.contributor.authorÖzcan, Mustafa
dc.contributor.authorTuran Maviş, Begüm
dc.contributor.authorŞar, Çağla
dc.contributor.authorÖzdemir, Fulya
dc.date.accessioned2026-01-14T11:59:32Z
dc.date.available2026-01-14T11:59:32Z
dc.date.issued2026
dc.departmentFakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.departmentFakülteler, Diş Hekimliği Fakültesi, Klinik Bilimler Bölümü, Ortodonti Ana Bilim Dalı
dc.description.abstractBackground/Objectives: The early and accurate identification of impacted teeth in the maxilla is critical for effective dental treatment planning. Traditional diagnostic methods relying on manual interpretation of radiographic images are often time-consuming and subject to variability. Methods: This study presents a deep learning-based approach for automated classification of impacted maxillary canines using panoramic radiographs. A comparative evaluation of four pre-trained convolutional neural network (CNN) architec tures—ResNet50, Xception, InceptionV3, and VGG16—was conducted through transfer learning techniques. In this retrospective single-center study, the dataset comprised 694 an notated panoramic radiographs sourced from the archives of a university dental hospital, with a mildly imbalanced representation of impacted and non-impacted cases. Models were assessed using accuracy, precision, recall, specificity, and F1-score. Results: Among the tested architectures, VGG16 demonstrated superior performance, achieving an accuracy of 99.28% and an F1-score of 99.43%. Additionally, a prototype diagnostic interface was developed to demonstrate the potential for clinical application. Conclusions: The findings underscore the potential of deep learning models, particularly VGG16, in enhancing diag nostic workflows; however, further validation on diverse, multi-center datasets is required to confirm clinical generalizability.
dc.identifier.citationTokatlı, N., Erdem, B., Özcan, M., Turan Maviş, B., Şar, Ç., & Özdemir, F. (2026). Comparative evaluation of deep learning models for the classification of impacted maxillary canines on panoramic radiographs. Diagnostics, 16(2), pp. 1-15. https://doi.org/10.3390/diagnostics16020219
dc.identifier.doi10.3390/diagnostics16020219
dc.identifier.endpage15
dc.identifier.issn2075-4418
dc.identifier.issue2
dc.identifier.scopusqualityQ2
dc.identifier.startpage1
dc.identifier.urihttps://doi.org/10.3390/diagnostics16020219
dc.identifier.urihttps://hdl.handle.net/20.500.13055/1242
dc.identifier.volume16
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.indekslendigikaynak.otherSCI-E - Science Citation Index Expanded
dc.institutionauthorTokatlı, Nazlı
dc.institutionauthorErdem, Buket
dc.institutionauthorÖzcan, Mustafa
dc.institutionauthorŞar, Çağla
dc.institutionauthorÖzdemir, Fulya
dc.institutionauthorid0000-0001-9840-4211
dc.institutionauthorid0009-0004-6316-6072
dc.institutionauthorid0009-0008-8331-9493
dc.institutionauthorid0000-0003-4966-9779
dc.institutionauthorid0000-0003-2460-0724
dc.language.isoen
dc.publisherMDPI Publishing
dc.relation.ispartofDiagnostics
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectDeep Learning
dc.subjectRadiography
dc.subjectPanoramic
dc.subjectCuspid
dc.subjectTooth
dc.subjectImpacted
dc.subjectArtificial Intelligence
dc.titleComparative evaluation of deep learning models for the classification of impacted maxillary canines on panoramic radiographs
dc.typeArticle
dspace.entity.typePublication

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Kapalı Erişim
İsim:
Tam Metin / Full Text
Boyut:
664.65 KB
Biçim:
Adobe Portable Document Format
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Kapalı Erişim
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Bilgisayar Mühendisliği Bölümü Koleksiyonu
Ortodonti Ana Bilim Dalı Koleksiyonu