Scholarlink

Objectives <p>This study aimed to develop and evaluate a deep convolutional neural network (CNN) model for the automatic segmentation of foreign bodies and ghost images in panoramic radiographs (PRs), which can complicate diagnostic interpretation.</p> Methods <p>A dataset of 11,226 PRs from four devices was annotated by two radiologists using the Computer Vision Annotation Tool. A U-Net-based CNN model was trained and evaluated using Intersection over Union (IoU), Dice coefficient, accuracy, precision, recall, and F1 score.</p> Results <p>For foreign body segmentation, the model achieved validation Dice and IoU scores of 0.9439 and 0.9043, and test scores of 0.9657 and 0.9371. For ghost image segmentation, validation Dice and IoU were 0.8234 and 0.7388, with test scores of 0.8749 and 0.8145. Overall test accuracy exceeded 0.999.</p> Conclusions <p>The AI model showed high accuracy in segmenting foreign bodies and ghost images in PRs, indicating its potential to assist radiologists. Further clinical validation is recommended.</p>

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

U-net-based segmentation of foreign bodies and ghost images in panoramic radiographs

  • 期刊论文

  • 发表日期：

    2025年9月17日

查看全文
  • Elif Çelebi,
  • Nurullah Akkaya,
  • Gürkan Ünsal

摘要

Objectives

This study aimed to develop and evaluate a deep convolutional neural network (CNN) model for the automatic segmentation of foreign bodies and ghost images in panoramic radiographs (PRs), which can complicate diagnostic interpretation.

Methods

A dataset of 11,226 PRs from four devices was annotated by two radiologists using the Computer Vision Annotation Tool. A U-Net-based CNN model was trained and evaluated using Intersection over Union (IoU), Dice coefficient, accuracy, precision, recall, and F1 score.

Results

For foreign body segmentation, the model achieved validation Dice and IoU scores of 0.9439 and 0.9043, and test scores of 0.9657 and 0.9371. For ghost image segmentation, validation Dice and IoU were 0.8234 and 0.7388, with test scores of 0.8749 and 0.8145. Overall test accuracy exceeded 0.999.

Conclusions

The AI model showed high accuracy in segmenting foreign bodies and ghost images in PRs, indicating its potential to assist radiologists. Further clinical validation is recommended.