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

Prompt-Sensitive Decision Behavior of Large Language Models in Intensive Care Unit Mortality Prediction for Spontaneous Intracerebral Hemorrhage: Comparative Benchmarking Study.

Journal of medical Internet research·2026

Same author

Traumatic common iliac artery occlusion mimicking acute sciatica: a case report.

Journal of surgical case reports·2026

Same author

Pre-injury hypercholesterolemia is associated with microbiota-associated neurobehavioral vulnerability following traumatic brain injury.

Brain, behavior, and immunity·2026

Same author

A Practical Gut-On-Chip Workflow for Imaging-Based Assessment of Epithelial Barrier Dynamics During E. coli Co-Culture.

Biotechnology and bioengineering·2026

Same author

Hydrophilicity-Enhanced NH<sub>2</sub>-MIL-88B(Fe) Integrated Photocatalytic Membrane Reactor for Simultaneous Rejection and Degradation of Low-Density Polyethylene in Water Matrices.

ACS applied materials & interfaces·2026

Same author

Mechanics of dust bathing in birds.

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

Search research articles

相关实验视频

Updated: Sep 14, 2025

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

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

Published on: February 23, 2024

深度学习的评估,以细粒度分类和后处理改进来检测.

Lin Yang¹, Guan-Yu Chen²

¹College of Electrical Engineering and New Energy, China Three Gorges University, Yichang, China.

International dental journal

|July 23, 2025

概括

这项研究使用先进的深度学习模型增强了牙检测,实现了更高的准确性和更精细的分类,以实现个性化治疗策略. 这些新方法改善了多个AI模型的检测,帮助牙医在临床护理中.

科学领域:

人工智能在牙科中的应用
对于医学成像的深度学习
牙科诊断牙科诊断牙科诊断

背景情况:

现有的用于检测牙损伤的深度学习缺乏全面的分类,并专注于有限的损伤区域.
需要先进的人工智能模型,能够检测牙实例和细粒度的分类.

研究的目的:

开发和评估先进的深度学习模型,用于基于牙实例的牙损伤检测.
实施使用国际虫检测和评估系统 (ICDAS) 标准对虫进行细粒度分类.
引入两种新的校正方法,以提高复杂场景中的模型稳定性和准确性.

主要方法:

利用1200张口腔内图像的数据集,增加到8754张图像与详细的牙注释.
训练并测试了三个最先进的深度学习模型:YOLO-v8,YOLO-v9和YOLO-NAS.
实施后处理校正技术,涉及加权平均得分和基于空间牙关系的自适应性信心调整.

主要成果:

建议的校正方法在YOLO模型中显著提高了平均精度 (mAP) 2.8%至4.7% (p < .01),YOLO-v8实现了72.9%的mAP.
总体精度和回忆分别增加了3.8%和5.6%,每秒 (FPS) 略有下降.
在检测中度虫和增强模型稳定性方面表现出显著的改进.

关键词:

人工智能的人工智能是人工智能.脏病检测脏病检测深度学习是一种深度学习.在口腔内拍摄的照片.

更多相关视频

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

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

Published on: April 14, 2023

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

相关实验视频

Last Updated: Sep 14, 2025

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

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

Published on: February 23, 2024

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

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

Published on: April 14, 2023

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

结论:

开发的正方法有效地增强了现有的AI框架,用于检测牙虫.
细粒度分类能力具有重要的临床价值,帮助牙医制定个性化治疗计划.
这项研究预计将推动人工智能在牙科中的应用,并刺激进一步的研究.