Truace
Subscribe

Evaluation of Differential Diagnosis of Odontogenic Lesions in Cone Beam Computed Tomography Images Using Radiomics-Based Machine Learning

Objective This study aimed to evaluate the structural characteristics of mandibular alveolar bone in patients with Type 1 diabetes mellitus (T1DM), Type 2 diabetes mellitus (T2DM), and systemically healthy controls using panoramic radiography-based radiomic analysis combined with machine learning algorithms. Materials and methods A total of 225 panoramic radiographs (75 T1DM, 75 T2DM, 75 healthy controls) were retrospectively analyzed. ROIs were segmented from eight anatomical mandibular segments per subject, an…

By the Truvace desk1 min read1 sourcePeer-reviewedTRV-2026-0844· cite & verify
Evaluation of Differential Diagnosis of Odontogenic Lesions in Cone Beam Computed Tomography Images Using Radiomics-Based Machine Learning
Calle Doctor Loureiro Crespo, plaza del Hospital Provincial - Pontevedra capital by Domi402. CC BY-SA 4.0 · https://creativecommons.org/licenses/by-sa/4.0

In brief

Objective This study aimed to evaluate the structural characteristics of mandibular alveolar bone in patients with Type 1 diabetes mellitus (T1DM), Type 2 diabetes mellitus (T2DM), and systemically healthy controls using panoramic radiography-based radiomic analysis combined with machine learning algorithms. Materials and methods A total of 225 panoramic radiographs (75 T1DM, 75 T2DM, 75 healthy controls) were retrospectively analyzed.

Four machine learning algorithms were evaluated: Random Forest, ExtraTrees, SVM-RBF, and Logistic Regression.

Main points

  1. Objective This study aimed to evaluate the structural characteristics of mandibular alveolar bone in patients with Type 1 diabetes mellitus (T1DM), Type 2 diabetes mellitus (T2DM), and systemically healthy controls using panoramic radiography-based radiomic analysis combined with machine learning algorithms.
  2. Materials and methods A total of 225 panoramic radiographs (75 T1DM, 75 T2DM, 75 healthy controls) were retrospectively analyzed.
  3. ROIs were segmented from eight anatomical mandibular segments per subject, and 107 radiomic features were extracted using PyRadiomics.

The gain

Evaluation of Differential Diagnosis of Odontogenic Lesions in Cone Beam Computed Tomography Images Using Radiomics-Based Machine Learning: The best single-segment performance was achieved in the left mandibular corpus with Logistic Regression (Accuracy=0.833, F1=0.832, AUC=0.958).

The rundown

ROIs were segmented from eight anatomical mandibular segments per subject, and 107 radiomic features were extracted using PyRadiomics. Interobserver reliability was confirmed by two-way random-effects ICC (≥0.85).

Sources

  1. Peer-reviewedDentomaxillofacial Radiology2026-08-21

The debate