Related Experiment Video
Updated: Sep 15, 2025
05:49
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
1.0K
Evaluation of Artificial Intelligent Systems Based Analysis in Dental Periapical Lesions - A Radiological Study
Giridhar Naidu1, Ramanpal Singh Makkad1, Fiza Khan1
1Department of Oral Medicine and Radiology, New Horizon Dental College and Research Institute Sakri, Bilaspur, Chhattisgarh, India.
Journal of Pharmacy & Bioallied Sciences
|July 14, 2025
Summary
Manual machine learning AI achieved 100% accuracy in diagnosing dental periapical lesions from CBCT scans, outperforming deep learning AI for better radiographic diagnosis.
Area of Science:
- Dentistry
- Radiology
- Artificial Intelligence
Background:
- Dental periapical lesions require accurate diagnosis for effective treatment.
- Cone-beam computed tomography (CBCT) is a key imaging modality for evaluating these lesions.
Purpose of the Study:
- To evaluate the efficacy of AI-based analysis for diagnosing dental periapical lesions using CBCT scans.
- To compare the diagnostic performance of manual machine learning (ML) AI and deep learning (DL) AI.
Main Methods:
- Analysis of 500 CBCT scans, with 400 used for AI training and 100 for validation.
- AI classification of lesions into periapical cysts, abscesses, or granulomas.
- Calculation of sensitivity, specificity, and accuracy for AI models and comparison with radiologist performance.
Main Results:
- Manual ML AI achieved 100% accuracy, while DL AI achieved 84.62% accuracy.
- Cysts presented with regular margins and cortical expansion; abscesses and granulomas showed hypodensity.
- Radiologists demonstrated high inter-observer agreement (0.98).
Conclusions:
- Manual machine learning AI demonstrates superior accuracy for radiographic diagnosis of periapical lesions compared to deep learning AI.
- AI holds significant potential to aid in the accurate radiographic diagnosis of dental periapical lesions.
