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

Fosfomycin as Oral Transition Therapy Versus Continued Intravenous β-Lactams for Complicated Urinary Tract Infections Caused by Extended-Spectrum β-Lactamase-Producing Enterobacterales: A Multicenter, Open-Label, Randomized Controlled Trial.

Clinical infectious diseases : an official publication of the Infectious Diseases Society of America·2026
Same author

Flexible infrared camouflage eutectic gallium-indium for thermoelectric energy harvesting.

Nature communications·2026
Same author

Impact of menopause on subfoveal choroidal thickness: population-based evidence from the 2017 to 2021 KNHANES.

Menopause (New York, N.Y.)·2026
Same author

Diverse structures of mcr-10-bearing plasmids and high colistin resistance in Enterobacter cloacae complex clinical isolates from South Korea.

International journal of antimicrobial agents·2026
Same author

Weekend Effect on Vitrectomy: Insights from a Nationwide Population-Based Study in Korea.

Ophthalmologica. Journal international d'ophtalmologie. International journal of ophthalmology. Zeitschrift fur Augenheilkunde·2026
Same author

The EphA3 Antibody Enhances CD47 Antibody-Mediated Phagocytosis by Repolarizing M2-Like Tumor-Associated Macrophages in a Preclinical Model of Recurrent Head and Neck Cancer.

OncoTargets and therapy·2026

相关实验视频

Updated: Jun 8, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K

自动化牙细分:基于3D UNet的方法与MIScnn框架.

Min Seok Kim1, Elie Amm1, Goli Parsi1

  • 1Department of Orthodontics and Dentofacial Orthopedics, Boston University Goldman School of Dentistry, Boston, Massachusetts.

Journal of the World federation of orthodontists
|November 3, 2024
PubMed
概括

从使用3D UNet卷积神经网络 (CNN) 的圆束计算机断层扫描 (CBCT) 来自动细分牙结构,显示出高精度. 这种人工智能驱动的方法为数字牙科工作流程中的手动细分提供了有效的替代方案.

关键词:
3D UNet 是一个 3D UNet 网络.人工智能的人工智能是人工智能.自动牙科细分系统 自动牙科细分系统卷积神经网络是一种卷积神经网络.语义细分 语义细分是指语义细分.

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
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: Jun 8, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
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:

  • 牙科 牙科是指牙科的专业.
  • 医疗成像医学成像
  • 人工智能的人工智能

背景情况:

  • 牙科的数字化工作流需要对形光束计算机断层扫描 (CBCT) 感兴趣的区域进行细分.
  • 手动细分是耗时和昂贵的,推动了对自动化解决方案的需求.
  • 卷积神经网络 (CNN) 为CBCT扫描细分提供了一种高效的自动化方法.

研究的目的:

  • 评估基于3DUNet的CNN模型的有效性,用于从CBCT扫描中自动细分大和下牙.
  • 将自动化方法的性能与传统的细分技术进行比较.

主要方法:

  • 使用医学图像分割CNN框架实现了一个3DUNet CNN模型.
  • 采用了351个CBCT扫描数据集,并使用了手动细分的基准真相标签.
  • 进行了数据预处理,增强和模型训练,以分析CNN的性能.

主要成果:

  • 该CNN模型在分割大牙和下牙方面取得了很高的准确性.
  • 平均子相似系数值为上牙的91.83%和下牙的91.35%.
  • 跨越欧盟的交叉点,精度和召回指标进一步验证了该模型的有效性.

结论:

  • 基于3D UNet的CNN模型有效地自动化了从CBCT扫描中对牙的细分.
  • 使用CNN的自动细分提供了准确和高效的结果,超过了手工方法.
  • 这项技术在改善牙科诊断和治疗规划过程方面具有重大潜力.