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

• Published in: Dento-maxillo-facial radiology Vol. 53; no. 5; pp. 316 - 324
• Main Authors: Song, Yang, Ma, Sirui, Mao, Bing, Xu, Kun, Liu, Yuan, Ma, Jingdong, Jia, Jun
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 28.06.2024
• Subjects: Adolescent; Adult; Aged; Algorithms; Ameloblastoma - diagnostic imaging; Ameloblastoma - pathology; Ameloblastoma - surgery; Cone-Beam Computed Tomography - methods; Diagnosis, Differential; Female; Humans; Jaw Neoplasms - diagnostic imaging; Jaw Neoplasms - surgery; Machine Learning; Male; Middle Aged; Odontogenic Cysts - diagnostic imaging; Odontogenic Cysts - surgery; Radiographic Image Interpretation, Computer-Assisted - methods; Radiomics; Retrospective Studies; radiomics; differential diagnosis; machine learning; cone-beam CT; odontogenic keratocyst; ameloblastoma
• ISSN: 0250-832X; 1476-542X; 1476-542X
• DOI: 10.1093/dmfr/twae016

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.