Title
Machine learning for classification of periodontal defects (vertical versus horizontal) using CBCT datasets
Authors
Sourav Panda1, Vishwannath Hiremath2,*, J Sophia Jeba Priya3, Nimisha Sanjay Pagare4, Rachita Mustilwar5 & Sunny Mavi6
Affiliation
1Department of Periodontics, Institute of Dental Sciences, Siksha O Anusandhan University, Bhubaneswar, India; 2Department of Oral and Maxillofacial Surgery, (A Unit of Hiremath Hospitals Pvt Ltd) Vijayanagar, Bangalore, India; 3Department of Oral Medicine and Radiology, Tamilnadu Government Dental College and hospital, Chennai, India; 4Department of Periodontology, Dr. D.Y. Patil Dental College and Hospital, Dr. D.Y. Patil Vidyapeeth (Deemed to be University), Pune, Maharashtra, India; 5Department of Periodontology, Rural Dental College, Pravara Institute of Medical Sciences, Maharashtra, India; 6Department of Periodontics, Sudha Rustagi College of Dental Sciences and Research, Faridabad, Haryana, India; *Corresponding author
Sourav Panda - E-mail: drsaurav87@gmail.com
Vishwannath Hiremath - E-mail: drhiremathhospitals@gmail.com
J Sophia Jeba Priya -E-mail: drsophia2@gmail.com
Nimisha Sanjay Pagare - E-mail: nimishapagare47@gmail.com
Rachita Mustilwar - E-mail: dr.rachu@gmail.com
Sunny Mavi - E-mail: snnymavi@gmail.com
Article Type
Research Article
Date
Received February 1, 2026; Revised February 28, 2026; Accepted February 28, 2026, Published February 28, 2026
Abstract
Accurate classification of periodontal bone defects is essential for treatment planning; yet conventional radiographic methods have limitations in complex anatomical regions. Therefore, it is of interest to develop and validated machine learning models to automatically classify periodontal bone defects using cone-beam computed tomography data from 1,847 teeth in 312 patients treated between January 2021 and December 2023. Convolutional neural networks, random forest, support vector machines and gradient boosting classifiers were trained using radiomic features and raw image data, with performance evaluated through five-fold cross-validation against expert consensus. The convolutional neural network achieved the highest performance with 91.4% accuracy, 89.8% sensitivity for vertical defects, 92.6% specificity for horizontal defects and an area under the ROC curve of 0.946. Thus, we show that machine learning; particularly deep learning approaches can reliably classify periodontal defect morphology on CBCT images and support improved diagnostic consistency and clinical decision-making in periodontology.
Keywords
Machine learning, periodontal defects, cone-beam computed tomography, deep learning, classification, artificial intelligence.
Citation
Panda et al. Bioinformation 22(2): 953-959 (2026)
Edited by
Hiroj Bagde
ISSN
0973-2063
Publisher
License
This is an Open Access article which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited. This is distributed under the terms of the Creative Commons Attribution License.
