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

Computed Tomography01:10

Computed Tomography

7.6K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
7.6K
Three-Dimensional Microscopy in Microbiology01:28

Three-Dimensional Microscopy in Microbiology

919
Three-dimensional imaging techniques are essential in cell biology, allowing researchers to visualize intricate cellular structures with high resolution. Two prominent methods, Differential Interference Contrast Microscopy (DIC) and Confocal Scanning Laser Microscopy (CSLM), provide distinct advantages for imaging live and thick specimens, respectively.Differential Interference Contrast MicroscopyDIC microscopy enhances contrast in transparent, unstained samples by converting phase...
919

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

Endodontic Management Before, During and After Head and Neck Radiotherapy: Biological, Diagnostic and Clinical Considerations in Head and Neck Cancer Patients.

International endodontic journal·2026
Same author

C-Shaped Canal Systems in Mandibular Second Molars: A Bibliometric Analysis and Review of Key Research Themes.

European endodontic journal·2026
Same author

Electric-Field-Tuned Consecutive Topological Phase Transitions between Distinct Correlated Insulators in Moiré MoTe_{2}/WSe_{2} Heterobilayer.

Physical review letters·2026
Same author

Automated Tooth Detection and Caries Identification in CBCT With Deep Learning.

International dental journal·2026
Same author

Picomolar chloramphenicol detection by orchestrating multi-level signal systems of metal-organic frameworks-catalytic hairpin assembly-gold nanoprobes.

Talanta·2026
Same author

Subcellular mass spectrometry reveals proteome remodeling in an asymmetrically dividing (frog) embryonic stem cell.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same journal

Effect of Pulpal Haemostasis Time on Partial Pulpotomy Outcome in Cariously Exposed Mature Permanent Teeth With Symptomatic Irreversible Pulpitis.

International endodontic journal·2026
Same journal

Endodontic Treatment of Apical Periodontitis Mitigates Systemic Inflammation and Restores the Blood-Brain Barrier Integrity in an In Vitro Model.

International endodontic journal·2026
Same journal

A Protocol for the Development of a Three-Dimensional Classification of Endodontic Lesions Scheduled for Surgery.

International endodontic journal·2026
Same journal

Understanding the Content and Purpose of S3 Clinical Practice Guidelines in Dentistry.

International endodontic journal·2026
Same journal

Histopathologic Validity and Clinical Reliability of Wolters Classification of Pulpitis: An Exploratory Study.

International endodontic journal·2026
Same journal

Short-Term Outcomes of Full Pulpotomy Compared With Root Canal Treatment for Irreversible Pulpitis: The PROVE Study.

International endodontic journal·2026
查看所有相关文章

相关实验视频

Updated: May 6, 2026

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

2.3K

从微型CT转移学习到三维根管形态识别的周周放射.

Weiwei Wu1,2, Jingyu Hu1,2, Bowen Shen3

  • 1Department of Stomatology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.

International endodontic journal
|February 23, 2026
PubMed
概括
此摘要是机器生成的。

转移学习有效地将3D解剖特征从微型CT扫描转移到周周放射,提高卷积神经网络 (CNN) 在识别根管形态方面的准确性. 这种多式联运方法在复杂的分类任务中显示出更大的好处.

关键词:
卷积神经网络是一种卷积神经网络.微型计算机断层扫描技术周围的X射线图是指周围的X射线图.根管形态 根管形态 根管形态转移学习转移学习

更多相关视频

Dynamic Navigation in Endodontics: Guided Access Cavity Preparation by Means of a Miniaturized Navigation System
07:03

Dynamic Navigation in Endodontics: Guided Access Cavity Preparation by Means of a Miniaturized Navigation System

Published on: May 5, 2022

5.4K
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

5.3K

相关实验视频

Last Updated: May 6, 2026

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

2.3K
Dynamic Navigation in Endodontics: Guided Access Cavity Preparation by Means of a Miniaturized Navigation System
07:03

Dynamic Navigation in Endodontics: Guided Access Cavity Preparation by Means of a Miniaturized Navigation System

Published on: May 5, 2022

5.4K
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

5.3K

科学领域:

  • 牙科成像和诊断牙科成像和诊断
  • 机器学习在医学中的应用
  • 放射学和解剖学研究

背景情况:

  • 精确识别根管形态对于内牙治疗成功至关重要.
  • 目前分析根管解剖的方法依赖于2D放射图,这可能会限制复杂的3D结构的可视化.
  • 多模式转移学习提供了一个潜在的解决方案,通过整合来自不同成像模式的数据来增强诊断能力.

研究的目的:

  • 研究隐性解剖特征从微型计算机断层扫描 (micro-CT) 转移到周围放射图的研究.
  • 评估多模式转移学习对3D根管形态识别的有效性.
  • 评估任务复杂度对转移学习模型性能的影响.

主要方法:

  • 使用微型CT扫描底第二牙 (MSMs),以创建虚拟放射图.
  • 临床模拟的周周放射图 (CSPRs) 是从ex vivo下产生的.
  • 四个卷积神经网络 (CNN) 架构使用不同的预训练策略进行训练,包括在ImageNet上预训练的模型和虚拟射线图.
  • 使用Grad-CAM可视化来解释模型的注意力,并将结果与内牙科住院医生的表现进行比较.

主要成果:

  • 与 ImageNet 预先训练的模型 (64.36%) 和内住院医生 (61.17%) 相比,在三类分类任务中,在虚拟射线图上预先训练的 CNN 实现了更高的准确性 (69.68%).
  • 格拉德-CAM分析显示,虚拟X光学预训练模型专注于相关的根结构,与ImageNet预训练模型不同.
  • 在一个简化的两类任务中,方法之间的性能差异在统计学上并不显著,这表明转移学习的好处在复杂的任务中更大.

结论:

  • 从微CT虚拟放射图片中隐含的3D特征可以通过转移学习有效地转移到CSPR.
  • 这种方法提高了CNN的解释性和诊断准确性,用于根管形态识别.
  • 多模式转移学习的有效性在复杂的多类分类任务中更为明显,为其在临床牙科成像中的应用提供了基础.