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

International endodontic journal·2026
Same author

Insights into the July 2026 Issue of the JOE.

Journal of endodontics·2026
Same author

CARES-A New Three-Dimensional Coding System for Classifying Teeth With Dens Invaginatus.

International endodontic journal·2026
Same author

Insights into the June 2026 Issue of the JOE.

Journal of endodontics·2026
Same author

Detection of maxillary sinusitis of endodontic origin in cone-beam CT images using deep learning algorithms.

Scientific reports·2026
Same author

Insights Into the May 2026 Issue of the JOE.

Journal of endodontics·2026
Same journal

Clinical Outcome of Replanted Avulsed Anterior Teeth: A Retrospective Cohort Study.

Journal of endodontics·2026
Same journal

Mahidol study 3: Post-operative Effect and Adverse Events of Regenerative Endodontic Procedures in Immature Permanent Teeth.

Journal of endodontics·2026
Same journal

Non-Surgical Management of Horizontal Root Fracture with Necrotic Apical Segment and Coronal Cervical Abfraction Using Mineral Trioxide Aggregate: Case Report.

Journal of endodontics·2026
Same journal

Identification of pain-related biomarkers and the associated potential molecular regulation mechanism in pulpitis by bioinformatics method.

Journal of endodontics·2026
Same journal

AI Prognostic Models in Endodontics: Scoping Review and Clinical Gap Analysis for Retreatment vs Microsurgery Decision Support.

Journal of endodontics·2026
Same journal

AI-based 3D measurement of root canal curvature from CBCT: Validation of an automated Schneider angle analysis.

Journal of endodontics·2026
查看所有相关文章

相关实验视频

Updated: Jul 10, 2025

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

2.8K

贝叶斯U-Net的基于不确定性的主动学习,用于多标签圆束CT细分的贝叶斯U-Net.

Jiayu Huang1, Nazbanoo Farpour2, Bingjian J Yang2

  • 1School of Computing and Augmented Intelligence Arizona State University, Tempe, Arizona.

Journal of endodontics
|November 18, 2023
PubMed
概括
此摘要是机器生成的。

积极学习 (AL) 策略显著提高了人工智能 (AI) 模型的准确性,用于检测和细分圆束CT (CBCT) 中的周围病变. 这种方法减少了在牙科AI开发中需要广泛的注释数据集的需求.

关键词:
人工智能的人工智能贝叶斯的U-Net是贝叶斯的U-Net.在CBCT中,CBCT是CBCT.积极学习是积极学习.深度学习是一种深度学习.多标签细分化的多标签细分化.周围的外皮病变.

更多相关视频

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.8K
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

2.5K

相关实验视频

Last Updated: Jul 10, 2025

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

2.8K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.8K
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

2.5K

科学领域:

  • 生物医学图像分析
  • 人工智能在牙科中的应用
  • 医学成像和诊断 医学成像和诊断

背景情况:

  • 训练人工智能进行生物医学图像分析需要大量的注释数据集.
  • 这项研究的重点是改进人工智能模型培训,用于在CBCT中检测周周病变.
  • 有限的数据集对在牙科中开发准确的人工智能模型构成了挑战.

研究的目的:

  • 评估积极学习 (AL) 策略对训练人工智能模型的有效性.
  • 改进CBCT中的多标签细分和检测周周病变.
  • 用有限的注释数据来评估AL策略.

主要方法:

  • 使用有限视野CBCT卷 (n=20) 进行培训.
  • 采用贝叶斯式U-Net,具有两个AL函数:贝叶斯式通过不同意 (BALD) 和Max_Entropy (ME) 的积极学习.
  • 将AL策略与非AL贝叶斯U-Net基准进行比较,评估细分精度 (Dice指数) 和病变检测.

主要成果:

  • 经过8次AL代,病变检测灵敏度达到BALD的84.0%,ME的76.0%,显著超过非AL贝叶斯U-Net (32.0%).
  • 与非AL基准指标 (0.680 ± 0.155) 相比,所有标签的平均子指数在AL策略中较高 (0.703 ± 0.166对于ME).
  • 在8次AL代后",损伤"的Dice指数为BALD的0.504和ME的0.501,明显高于非AL模型的0.288.1的最大值.

结论:

  • 主动学习策略,特别是BALD和ME,提高AI模型的准确性,用于CBCT的细分和病变检测.
  • 借助不确定性量化,AL有效地减少了对牙科AI广泛数据注释的需求.
  • 这种方法有望在牙科生物医学图像分析中更有效地开发人工智能工具.