Scholarlink

Dental abnormalities detection from radiographs is vital during dental treatment. Clinicians spend an arduous amount of time for oral diagnosis and analyzing the radiograph manually to check if any dental ailment is present. This process can sometimes cause misinterpretation due to lack of dentist experience or workload stress. Hence, this chapter introduces a recent deep learning state of model to automatically interpret the radiographs and expeditiously deliver the output.YOLO11 includes new module to perform enhanced feature detection. It is evaluated on a custom dataset of panoramic images annotated for four different classes (caries, fillings, root canal treated tooth and impacted tooth). The model attained a Precision of 0.808 on all classes, recall of 0.773, mAP 50 of 0.809 and mAP 95 of 0.482 respectively. The proposed method could assist the dentist in their workflow and elevate the quality of dental treatment in future.

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

Automatic Panoramic Radiographs Segmentation for Dental Disease Detection Using YOLO11

  • 章节

  • 发表日期：

    2026年

查看全文
  • Priscilla Whitin,
  • S. Sivakumar,
  • Vinayakumar Ravi,
  • K. Anish Pon Yamini,
  • S. Jebarose Juliyana,
  • K. Suthendran

摘要

Dental abnormalities detection from radiographs is vital during dental treatment. Clinicians spend an arduous amount of time for oral diagnosis and analyzing the radiograph manually to check if any dental ailment is present. This process can sometimes cause misinterpretation due to lack of dentist experience or workload stress. Hence, this chapter introduces a recent deep learning state of model to automatically interpret the radiographs and expeditiously deliver the output.YOLO11 includes new module to perform enhanced feature detection. It is evaluated on a custom dataset of panoramic images annotated for four different classes (caries, fillings, root canal treated tooth and impacted tooth). The model attained a Precision of 0.808 on all classes, recall of 0.773, mAP 50 of 0.809 and mAP 95 of 0.482 respectively. The proposed method could assist the dentist in their workflow and elevate the quality of dental treatment in future.