Deep Learning Based Evaluation of Skeletal Maturation: A Comparative Analysis of Five Hand-Wrist Methods

Basit Öğe Kaydı
dc.contributor.authorTentas, Serhat
dc.contributor.authorOzden, Samet
dc.date.accessioned2026-04-04T13:33:19Z
dc.date.available2026-04-04T13:33:19Z
dc.date.issued2025
dc.departmentİnönü Üniversitesi
dc.description.abstractObjectiveThe study aims to evaluate the effectiveness of deep learning algorithms in skeletal age estimation by comparing the diagnostic reliability of five different hand-wrist maturation (HWM) assessment methods.Materials and MethodsA total of 6572 hand-wrist radiographs from orthodontic patients aged 8-16 years were retrospectively analysed. Radiographs were categorised into five groups based on HWM classification methods: (I) Bj & ouml;rk's nine-stage, (II) H & auml;gg and Taranger's five-stage, (III) Chapman's four-stage, (IV) three-stage hook of hamate ossification based and (V) simplified three-stage Bj & ouml;rk's classification based. YOLOv8x-based deep learning models were trained separately for each group. The dataset was split into training, validation and test subsets. Performance was evaluated using accuracy, precision, recall, F1 score and AUC metrics.ResultsThe YOLOv8x-cls model demonstrated high classification performance across all five groups. Group IV and Group II achieved the highest accuracy and F1 scores, with average F1 values of 0.99 and 0.96, respectively. Group III and Group V also showed strong performance (F1 = 0.93 and 0.92). In Group I, slightly lower classification performance was observed in the S-H2 and MP3-Cap stages (F1 = 0.72-0.74), which correspond to the pubertal growth peak, while early and late skeletal maturation stages were classified with high accuracy and F1 scores. ROC curve analysis further supported these findings, with AUC values for MP3-Cap and S-H2 recorded as 0.70 and 0.75, respectively, whereas higher AUC values were achieved in most other stages across all groups.ConclusionDeep learning models proved effective in evaluating skeletal maturation across five different HWM methods. Particularly high performance was observed in anatomically distinct regions such as the MP3, adductor sesamoid and hamate bone, which can be reliably identified by general dentists, enabling earlier referrals and timely orthodontic interventions.
dc.description.sponsorshipScientific Research Projects Coordination Unit of Idot;noenue University [TDH-2024-3439]
dc.description.sponsorshipThis research was supported by the Scientific Research Projects Coordination Unit of & Idot;noenue University under project number TDH-2024-3439.
dc.identifier.doi10.1111/ocr.70008
dc.identifier.endpage954
dc.identifier.issn1601-6335
dc.identifier.issn1601-6343
dc.identifier.issue6
dc.identifier.orcid0000-0002-9733-9777
dc.identifier.pmid40704688
dc.identifier.scopus2-s2.0-105011827543
dc.identifier.scopusqualityQ1
dc.identifier.startpage943
dc.identifier.urihttps://doi.org/10.1111/ocr.70008
dc.identifier.urihttps://hdl.handle.net/11616/109079
dc.identifier.volume28
dc.identifier.wosWOS:001534625400001
dc.identifier.wosqualityQ3
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.language.isoen
dc.publisherWiley
dc.relation.ispartofOrthodontics & Craniofacial Research
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WOS_20250329
dc.subjectartificial intelligence
dc.subjectbone age
dc.subjectdeep learning
dc.subjectskeletal maturation
dc.titleDeep Learning Based Evaluation of Skeletal Maturation: A Comparative Analysis of Five Hand-Wrist Methods
dc.typeArticle

Dosyalar

Koleksiyon

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