相关实验视频

Updated: Jan 20, 2026

Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System

Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System

Published on: May 3, 2018

走向自动化模型分析:3D牙科扫描的多视图AI细分

Zaw Htet Aung¹, Sangsan Noppadolmongkol², Nuttida Suwunnapang²

¹Lecturer, Department of Orthodontics, Faculty of Dentistry, Mahidol University, Bangkok, Thailand.

Journal of the World federation of orthodontists

|January 18, 2026

概括

这项研究引入了一个人工智能模型,用于精确的牙和牙边界细分在3D口腔内扫描,减少手工工作在正. 人工智能方法在临床数据上实现了高精度,支持高效的数字模型分析.

科学领域:

生物医学工程生物医学工程
计算机科学计算机科学
牙科技术牙科技术

背景情况:

准确识别牙和牙边界对于正牙诊断,治疗计划和器械制造至关重要.
在数字模型中手动对这些边界进行细分是耗时且容易变化的.
人工智能 (AI) 提供了提高准确性和效率的自动化这一过程的潜力.

研究的目的:

开发和评估基于人工智能的多视图细分方法,用于在3D口腔内扫描中自动识别牙和牙边界.
通过人工智能驱动的解决方案来减少手工工作量并支持日常正牙工作流程.
在公共和临床数据集上评估拟议的AI模型的准确性和通用性.

主要方法:

利用了来自3D牙挑战数据集的1200个牙科模型和29个临床3D口腔内扫描.
使用修改的多视图方法将3D模型转换为多个2D图像.
训练了一种基于Mask2Former架构的AI细分模型,用于自动划分牙边界,使用平均交叉与联盟 (mIoU) 和子相似系数 (DICE) 评分进行评估.

主要成果:

人工智能模型在公共和临床数据集上实现了高精度.
在公共测试数据集上获得了93.1%的mIoU和95.7%的DICE.
在临床测试组中,mIoU为90.7%,DICE为94.9%,即使扫描质量不同,也表现出强烈的概括性.

结论:

基于人工智能的修改多视图细分模型显示了 ортодонтика内口腔扫描的显著临床潜力.
该方法提供了准确的细分结果,提高了数字模型分析的效率.
该模型对于日常的临床整合到日常的正统牙科工作流程是有前途的.

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.数字工作流的数字工作流.在口腔内扫描.矯正牙科矯正牙科是一種矯正牙科.牙细分是指牙的细分.

更多相关视频

Accuracy in Dental Medicine, A New Way to Measure Trueness and Precision

Accuracy in Dental Medicine, A New Way to Measure Trueness and Precision

Published on: April 29, 2014

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

相关概念视频

Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System

Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System

Here we describe a protocol for the automated segmentation of fluorescently labeled tissues on slides using a widefield high-content analysis system (WHCAS). This protocol has wide-ranging applications in any field which involves the quantitation of fluorescent markers in biological tissues including the biological sciences, medical engineering, and health...

Accuracy in Dental Medicine, A New Way to Measure Trueness and Precision

Accuracy in Dental Medicine, A New Way to Measure Trueness and Precision

Accuracy is a major demand in dental medicine. To verify accuracy, reference scanners are needed. This article presents a new reference scanner with an adjusted scanning method to acquire a broad variety of dental morphologies with high trueness and...

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

The bottleneck for cellular 3D electron microscopy is feature extraction (segmentation) in highly complex 3D density maps. We have developed a set of criteria, which provides guidance regarding which segmentation approach (manual, semi-automated, or automated) is best suited for different data types, thus providing a starting point for effective...

Semi-Automated Planimetric Quantification of Dental Plaque Using an Intraoral Fluorescence Camera

Semi-Automated Planimetric Quantification of Dental Plaque Using an Intraoral Fluorescence Camera

This study presents a semi-automated digital image analysis procedure for the planimetric quantification of disclosed dental plaque based on images acquired with an intraoral fluorescence camera. The method allows for the rapid and reliable quantification of dental plaque in the research...

Semi-Automated Phenotypic Analysis of Functional 3D Spheroid Cell Cultures

Semi-Automated Phenotypic Analysis of Functional 3D Spheroid Cell Cultures

We present a protocol for growing high-reproducible spheroids and their phenotypic characterization using image capture and...

Measuring Maxillary Posterior Tooth Movement: A Model Assessment using Palatal and Dental Superimposition

Measuring Maxillary Posterior Tooth Movement: A Model Assessment using Palatal and Dental Superimposition

This manuscript presents a comprehensive protocol to evaluate the three-dimensional (3D) movement of maxillary posterior teeth with clear aligners using digital model superimposition, an invaluable tool in orthodontics and dentofacial...