Scholarlink

Oral diseases often remain undetected by the naked eye until they reach advanced stages. This challenge can be addressed through the use of sophisticated algorithms capable of identifying common dental conditions—such as impaction and carcinoma—early and with high accuracy. This study explores the use of deep learning techniques for classifying dental diseases through orthopantomogram (OPG) images. Within the domain of dental informatics, it evaluates the performance of advanced neural network models, including ResNet v2, YOLO v5, and YOLO v8. The approach involves constructing a custom, annotated dataset of OPG images, applying comprehensive data augmentation strategies, and training the models using platforms like Google Colab and Roboflow. Results show that YOLO v5 delivered superior performance, with a precision of 0.90, recall of 0.96, and an overall accuracy of 97.06%. In conclusion, this research highlights the effectiveness of deep learning in automating dental disease diagnosis, offering considerable support to healthcare providers—particularly in underserved or remote regions with limited access to specialist care.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep Learning Based Multi-Class Classification of Dental Diseases Using OPG Images

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Anmol Arun,
  • Rupali Patil,
  • Bipin Upadhyay

摘要

Oral diseases often remain undetected by the naked eye until they reach advanced stages. This challenge can be addressed through the use of sophisticated algorithms capable of identifying common dental conditions—such as impaction and carcinoma—early and with high accuracy. This study explores the use of deep learning techniques for classifying dental diseases through orthopantomogram (OPG) images. Within the domain of dental informatics, it evaluates the performance of advanced neural network models, including ResNet v2, YOLO v5, and YOLO v8. The approach involves constructing a custom, annotated dataset of OPG images, applying comprehensive data augmentation strategies, and training the models using platforms like Google Colab and Roboflow. Results show that YOLO v5 delivered superior performance, with a precision of 0.90, recall of 0.96, and an overall accuracy of 97.06%. In conclusion, this research highlights the effectiveness of deep learning in automating dental disease diagnosis, offering considerable support to healthcare providers—particularly in underserved or remote regions with limited access to specialist care.