Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

A rat muscle contusion model created by a modified drop-mass method using ultrasound.

Bone & joint research·2026
Same author

Core Temperature Estimation Using Wearable Earbud-Type Thermometer and Machine Learning During Light-Intensity Cycling Under Varying Indoor Ambient Temperatures.

Scandinavian journal of medicine & science in sports·2026
Same author

Bmal1 regulates thermogenic function by modulation of lipolytic and oxidative phosphorylation gene expression in male mice brown adipocytes.

Endocrinology·2026
Same author

Association Between Underweight Status and Social Jet Lag Among Japanese University Students: A Cross-Sectional Study with Sex-Specific Analysis.

Yonago acta medica·2026
Same author

Biomechanical assessment of the maxillary position after Le Fort I osteotomy using rapidly biodegradable miniplates and screws: an experimental study.

International journal of medical sciences·2026
Same author

Surgical hematoma removal promotes skeletal muscle recovery in a rat laceration model.

Scientific reports·2026

相关实验视频

Updated: May 30, 2025

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

763

优化牙植入物识别使用深度学习利用人工数据.

Shintaro Sukegawa1,2, Kazumasa Yoshii3, Takeshi Hara4,5

  • 1Department of Oral and Maxillofacial Surgery, Faculty of Medicine, Kagawa University, 1750-1, Ikenobe, Miki-cho, Kita-gun, Takamatsu, 761-0793, Kagawa, Japan. gouwan19@gmail.com.

Scientific reports
|January 29, 2025
PubMed
概括

生成人工牙植入物图像提高了全景X射线的分类准确性. 这种深度学习方法通过以现实合成图像补充真实世界的数据来提高诊断性能.

关键词:
人工图像生成的人工图像生成分类的准确性分类的准确性深度学习是一种深度学习.牙植入物是如何使用的全景X射线影像,可以看到.

更多相关视频

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.7K
Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities
07:14

Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities

Published on: May 24, 2022

4.3K

相关实验视频

Last Updated: May 30, 2025

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

763
Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.7K
Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities
07:14

Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities

Published on: May 24, 2022

4.3K

科学领域:

  • 生物医学成像技术 生物医学成像技术
  • 人工智能在牙科中的应用
  • 深度学习用于医学诊断

背景情况:

  • 准确的牙植入物分类对于诊断和治疗计划至关重要.
  • 现有的深度学习模型数据集可能缺乏多样性和体积.
  • 人工图像生成为增强有限数据集提供了一个潜在的解决方案.

研究的目的:

  • 评估结合人工生成的牙植入物图像对分类性能的影响.
  • 为了比较不同的人工图像生成策略的有效性.
  • 提高使用全景X射线识别牙植入物的深度学习模型的准确性.

主要方法:

  • 一个包含7946个体内牙植入物图像的数据集被人工生成的图像补充.
  • 使用三维扫描创建植入物表面模型用于图像生成.
  • 使用ResNet50深度学习模型,将10种类型的牙科植入物分类为三个数据集:体内,无背景调整的人工和具有背景调整的人工.

主要成果:

  • 在体内图像 (数据集A) 的分类精度为0.8888.8.
  • 没有背景调整的人工图像 (数据集B) 的精度为0.903.
  • 有背景调整的人造图像 (数据集C) 的精度最高,为0.9146,显示最佳特征分布.

结论:

  • 结合人工生成的牙植入物的X射线图像显著提高了深度学习分类模型的性能.
  • 人工图像生成,特别是具有背景调整,是改善牙植入物分类准确性的有益策略.
  • 这种方法在牙科中使用全景射线图进行人工智能驱动的诊断方面显示出前景.