EUVIMEDEUVIMED entdecken
Open Access

Application of machine learning in the preoperative radiomic diagnosis of ameloblastoma and odontogenic keratocyst based on cone-beam CT

Yang Song iD, Sirui Ma, Bing Mao, Kun Xu, Yuan Liu, Jingdong Ma, Jun Jia

Dentomaxillofacial Radiology · 28.06.2024 · 53 (5) · 316-324

DOI: 10.1093/dmfr/twae016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Dentomaxillofacial Radiology, online erschienen am 16.04.2024. Verfasst von Yang Song und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Medicine and Health Management, Huazhong University of Science & Technology, Hangkong Road, Wuhan, 430030, China. Hauptthemen laut MEDLINE: Cone-Beam Computed Tomography, Machine Learning, Ameloblastoma, Odontogenic Cysts. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Preoperative diagnosis of oral ameloblastoma (AME) and odontogenic keratocyst (OKC) has been a challenge in dentistry. This study uses radiomics approaches and machine learning (ML) algorithms to characterize cone-beam CT (CBCT) image features for the preoperative differential diagnosis of AME and OKC and compares ML algorithms to expert radiologists to validate performance.

Methods

We retrospectively collected the data of 326 patients with AME and OKC, where all diagnoses were confirmed by histopathologic tests. A total of 348 features were selected to train six ML models for differential diagnosis by a 5-fold cross-validation. We then compared the performance of ML-based diagnoses to those of radiologists.

Results

Among the six ML models, XGBoost was effective in distinguishing AME and OKC in CBCT images, with its classification performance outperforming the other models. The mean precision, recall, accuracy, F1-score, and area under the curve (AUC) were 0.900, 0.807, 0.843, 0.841, and 0.872, respectively. Compared to the diagnostics by radiologists, ML-based radiomic diagnostics performed better.

Conclusions

Radiomic-based ML algorithms allow CBCT images of AME and OKC to be distinguished accurately, facilitating the preoperative differential diagnosis of AME and OKC. Advances in knowledge ML and radiomic approaches with high-resolution CBCT images provide new insights into the differential diagnosis of AME and OKC.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cone-Beam Computed TomographyMachine LearningAmeloblastomaOdontogenic CystsHumansRetrospective StudiesFemaleMaleDiagnosis, DifferentialAdultMiddle AgedAlgorithmsAdolescentAgedJaw NeoplasmsRadiographic Image Interpretation, Computer-AssistedRadiomics

Stichwörter der Autor:innen

ameloblastomacone-beam CTdifferential diagnosismachine learningodontogenic keratocystradiomics

Autor:innen und Institutionen

  • School of Medicine and Health Management, Huazhong University of Science & Technology, Hangkong Road, Wuhan, 430030, China.
  • State Key Laboratory of Oral & Maxillofacial Reconstruction and Regeneration, Key Laboratory of Oral Biomedicine Ministry of Education, Hubei Key Laboratory of Stomatology, School & Hospital of Stomatology, Wuhan Univer…
  • Department of Oral and Maxillofacial-Head and Neck Oncology, School and Hospital of Stomatology, Wuhan University, Luoyu Road, Wuhan, 430072, China.
  • Zhengzhou University People's Hospital (Henan Provincial People's Hospital), Weiwu Road, Zhengzhou, 450003, China.

ORCID-Profile: Yang Song

Zitieren

APA

Song, Y., Ma, S., Mao, B., Xu, K., Liu, Y., Ma, J., & Jia, J. (2024). Application of machine learning in the preoperative radiomic diagnosis of ameloblastoma and odontogenic keratocyst based on cone-beam CT. Dentomaxillofacial Radiology, 53(5), 316-324. https://doi.org/10.1093/dmfr/twae016

Vancouver

Song Y, Ma S, Mao B, Xu K, Liu Y, Ma J, et al. Application of machine learning in the preoperative radiomic diagnosis of ameloblastoma and odontogenic keratocyst based on cone-beam CT. Dentomaxillofacial Radiology. 2024;53(5):316-324. doi:10.1093/dmfr/twae016

BibTeX
@article{Song2024,
  author = {Song, Yang and Ma, Sirui and Mao, Bing and Xu, Kun and Liu, Yuan and Ma, Jingdong and Jia, Jun},
  title = {Application of machine learning in the preoperative radiomic diagnosis of ameloblastoma and odontogenic keratocyst based on cone-beam CT},
  journal = {Dentomaxillofacial Radiology},
  year = {2024},
  volume = {53},
  number = {5},
  pages = {316--324},
  doi = {10.1093/dmfr/twae016}
}
Kostenlos starten →