Development of a highly accurate machine learning model for the differential diagnosis of ameloblastoma and odontogenic keratocyst on computed tomography images
Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology · 2026
DOI: 10.1016/j.oooo.2026.01.026 ↗Kurz gefasst
Fachartikel in der Zeitschrift Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology, 2026. Verfasst von Daisuke Nomoto und 5 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Dentistry (First Department of Oral and Maxillofacial Surgery), Osaka Dental University, Hirakata, Osaka, Japan. Electronic addres…. Hauptthemen laut MEDLINE: Machine Learning, Odontogenic Cysts, Ameloblastoma, Tomography, X-Ray Computed. Die Arbeit nennt 47 Literaturangaben.
Abstract (Originalsprache)
OBJECTIVE: To develop a machine learning model using computed tomography (CT) images for preoperative differential diagnosis of ameloblastoma (AM) and odontogenic keratocyst (OKC), and to compare its performance with that of an oral and maxillofacial radiologist. STUDY DESIGN: This retrospective study analyzed CT images from 154 patients (70 AM, 84 OKC). Seventeen clinical and imaging features were extracted and compiled into a CSV file. The data were randomly divided into five subsets for five-fold cross-validation. In each fold, 80% of the data were used for training and 20% for testing. Two machine learning models-Prediction One and Random Forest-were trained on the training data and evaluated on the test data. Diagnostic performance was assessed using receiver operating characteristic (ROC) curves, and the AUC were calculated. The performance of each model was compared with that of a radiologist blinded to clinical data. Variable importance was also analyzed to identify key diagnostic features. RESULTS: Prediction One achieved an AUC of 0.95. Random Forest achieved an AUC of 0.96. Both models significantly outperformed the radiologist (AUC: 0.80, P < .05). The most influential diagnostic features were root resorption and locularity. CONCLUSION: Machine learning models accurately distinguished AM from OKC and may assist preoperative diagnosis and planning.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Graduate School of Dentistry (First Department of Oral and Maxillofacial Surgery), Osaka Dental University, Hirakata, Osaka, Japan. Electronic address: nomoto-d@cc.osaka-dent.ac.jp.
- Department of Oral Radiology, Osaka Dental University, Hirakata, Osaka, Japan.
- First Department of Oral and Maxillofacial Surgery, Osaka Dental University, Hirakata, Osaka, Japan.
Zitieren
APA
Nomoto, D., Fukuda, M., Ariji, Y., Nakanishi, T., Tsuji, K., & Kubo, H. (2026). Development of a highly accurate machine learning model for the differential diagnosis of ameloblastoma and odontogenic keratocyst on computed tomography images. Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology. https://doi.org/10.1016/j.oooo.2026.01.026
Vancouver
Nomoto D, Fukuda M, Ariji Y, Nakanishi T, Tsuji K, Kubo H. Development of a highly accurate machine learning model for the differential diagnosis of ameloblastoma and odontogenic keratocyst on computed tomography images. Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology. 2026. doi:10.1016/j.oooo.2026.01.026
BibTeX
@article{Nomoto2026,
author = {Nomoto, Daisuke and Fukuda, Motoki and Ariji, Yoshiko and Nakanishi, Tamaki and Tsuji, Kaname and Kubo, Hirohito},
title = {Development of a highly accurate machine learning model for the differential diagnosis of ameloblastoma and odontogenic keratocyst on computed tomography images},
journal = {Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology},
year = {2026},
doi = {10.1016/j.oooo.2026.01.026}
}
EUVIMED