Explainable Deep Learning Framework for Periodontal Diagnosis in Dental Imaging
Preprint
- 1 October 2025
- preprint
- Published by Springer Nature in Research Square
Abstract
Periodontal disease is a chronic inflammatory condition impacting tooth-supporting structures. Early detection via radiographic analysis is essential to prevent progression and tooth loss. However, radiograph interpretation remains subjective and reliant on clinical expertise. This study presents an automated diagnostic framework using a Convolutional Neural Network (CNN) combined with Explainable Artificial Intelligence (XAI) through Gradient-weighted Class Activation Mapping (Grad-CAM). The system classifies periapical dental radiographs into periodontal and normal categories. The proposed CNN includes four convolutional layers with ReLU activation, max-pooling, and two fully connected layers. Data augmentation improved generalizability, and training employed the Stochastic Gradient Descent with Momentum (SGDM) algorithm. The model achieved a 94.17% classification accuracy with stable convergence. Grad-CAM heatmaps highlighted relevant regions influencing the model's decisions. In periodontal cases, alveolar bone loss was consistently identified, while normal images showed no pathological patterns. This visualization enhances interpretability and clinical trust. The integration of CNN and Grad-CAM offers a reliable, transparent diagnostic tool for dental radiology and supports the ethical adoption of AI in healthcare.Keywords
All Related Versions
This publication has 36 references indexed in Scilit:
- Dysbiosis linking periodontal disease and oral squamous cell carcinoma-A brief narrative reviewHeliyon, 2024
- A review of advancements of artificial intelligence in dentistryDentistry Review, 2024
- Effect of Periodontal Treatment on Reducing Chronic Inflammation in Systemically Healthy Patients With Periodontal DiseaseThe American Journal of Medicine, 2023
- Identification of disease-associate variants of aggressive periodontitis using genome-wide association studiesJapanese Dental Science Review, 2023
- Association of Serum Vitamin D With Periodontal DiseaseInternational Dental Journal, 2023
- Automatic recognition of teeth and periodontal bone loss measurement in digital radiographs using deep-learning artificial intelligenceJournal of Dental Sciences, 2023
- Translating periodontal data to knowledge in a learning health systemThe Journal of the American Dental Association, 2022
- Estimation of Alveolar Bone Loss in Periodontitis Using Machine LearningInternational Dental Journal, 2022
- Real‑time COVID-19 diagnosis from X-Ray images using deep CNN and extreme learning machines stabilized by chimp optimization algorithmBiomedical Signal Processing and Control, 2021
- Flowcharts for Easy Periodontal Diagnosis Based on the 2018 New Periodontal ClassificationClinical Advances in Periodontics, 2020