Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Impact of a Community-Based Preventive Oral Health Program on Oral Health-Related Quality of Life in School-Aged Children.

International journal of paediatric dentistry·2026

Same author

Psychometric evaluation of the Korean version of the Child Oral Health Impact Profile Short Form (COHIP-SF 19): a cross-sectional study.

Health and quality of life outcomes·2026

Same author

Adhesion of Newly Developed Composite Resin Splinting Materials to Enamel: Effect of Enamel Surface Treatment.

Dental traumatology : official publication of International Association for Dental Traumatology·2026

Same author

Novel <i>ITGB6</i> Mutations Causing Amelogenesis Imperfecta.

Genes·2026

Same author

Exploratory Evaluation of a Sodium Iodide-Based Root Canal Filling Formulation in a Canine Model of <i>Enterococcus faecalis</i>-Induced Periapical Inflammation.

Pharmaceutics·2026

Same author

From Belief to Behavior: Closing the Knowledge-Practice Gap in Irritable Bowel Syndrome Self-management.

Journal of neurogastroenterology and motility·2026

Search research articles

相关实验视频

Updated: Jun 26, 2025

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

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

Published on: November 30, 2022

使用深度学习对受影响的 mesiodens 的图像细分.

Hyuntae Kim¹, Ji-Soo Song², Teo Jeon Shin²

¹Department of Pediatric Dentistry, Seoul National University Dental Hospital, 03080 Seoul, Republic of Korea.

The Journal of clinical pediatric dentistry

|May 17, 2024

概括

此摘要是机器生成的。

深度学习算法在儿童牙科X射线中检测受冲击的 mesiodens (一种牙冲击) 中显示出高准确度. 这些人工智能工具为人类专家提供了可比的诊断性能,但速度要快得多.

关键词:

人工智能的人工智能是人工智能.深度学习是一种深度学习.弥赛亚是一个人.全景射线图 (Panoramic Radiography) 是一个全景射线图.语义细分语义细分是指语义细分.这就是U-Net.

更多相关视频

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

相关实验视频

Last Updated: Jun 26, 2025

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

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

Published on: November 30, 2022

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

科学领域:

牙科牙科是指牙科的专业.
人工智能的人工智能
医疗成像医学成像

背景情况:

受冲击的牙是儿童常见的牙异常,需要准确及时诊断.
早期检测 mesiodens 对于有效的正义牙科和手术干预至关重要.
传统的诊断方法可能会耗费大量时间,并且从业者之间的准确性可能会有所不同.

研究的目的:

评估深度学习算法的性能,用于在儿科全景放射图中对受影响的 mesiodens 进行分类和细分.
将深度学习模型的诊断准确性和效率与人类专家的性能进行比较.
以ResNet模型增强的U-Net算法的细分能力进行评估.

主要方法:

使用了850张儿科全景放射图 (年龄为3-9岁) 的数据集.
用预先训练的ResNet模型增强的U-Net语义细分算法用于mesiodens检测.
性能指标包括雅卡德指数,子系数,准确度,精度,回忆,F1分数和诊断时间.
对人类专家的诊断进行了比较,使用科恩的kappa统计数据.

主要成果:

深度学习模型实现了高细分性能 (Jaccard指数和Dice系数>90%).
诊断准确度 (91-92%) 和F1评分 (94-95%) 与人类专家 (96%) 相同.
人工智能模型在7.5秒内诊断出了 mesiodens,比人类群体快得多,并且与中度一致 (科恩的kappa = 0.767).

结论:

深度学习算法展示了对受影响的数据密度的强大细分能力.
人工智能驱动的诊断工具在准确性和F1分数方面提供了与人类专家可比的性能.
建议的深度学习方法显著减少了在儿科牙科放射学中检测 mesiodens 的诊断时间.