CAVITY DETECTION IN DENTAL IMAGES USING DEEP LEARNIING
Loading...
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
UNIVERSITI MALAYSIA SARAWAK
Abstract
Description
Dental cavities is a prevalent oral health issue, particularly in underserved and rural communities where access to professional dental care is limited. This study proposes a deep learning-based approach for automated cavity detection in intraoral dental images. A modified YOLOv8 object detection model was trained using a dataset comprising various dental conditions, sourced from public repositories and manually curated images. The methodology involved data preprocessing techniques such as resizing, normalization, and augmentation to enhance model generalization. The system was designed as a web-based platform, enabling users to upload images for cavity detection. Model performance was evaluated using accuracy, precision, recall, and F1-score, demonstrating significant potential for clinical and non-clinical applications. Results indicate that the proposed system effectively identifies cavities with accuracy of 89%, offering a cost-effective, accessible solution for early caries detection. This research contributes to the advancement of AI-driven dental diagnostics, reducing the dependency on expensive equipment and improving oral healthcare accessibility.