Jun-Ho Moon, Min-Gyu Kim, Sung Joo Cho, Dong-Yub Ko, Hye-Won Hwang, Ji-Ae Park, Shin-Jae Lee
{"title":"Evaluation of automated photograph-cephalogram image integration using artificial intelligence models.","authors":"Jun-Ho Moon, Min-Gyu Kim, Sung Joo Cho, Dong-Yub Ko, Hye-Won Hwang, Ji-Ae Park, Shin-Jae Lee","doi":"10.2319/010124-1.1","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>To develop and evaluate an automated method for combining a digital photograph with a lateral cephalogram.</p><p><strong>Materials and methods: </strong>A total of 985 digital photographs were collected and soft tissue landmarks were manually detected. Then 2500 lateral cephalograms were collected, and corresponding soft tissue landmarks were manually detected. Using the images and landmark identification information, two different artificial intelligence (AI) models-one for detecting soft tissue on photographs and the other for identifying soft tissue on cephalograms-were developed using different deep-learning algorithms. The digital photographs were rotated, scaled, and shifted to minimize the squared sum of distances between the soft tissue landmarks identified by the two different AI models. As a validation process, eight soft tissue landmarks were selected on digital photographs and lateral cephalometric radiographs from 100 additionally collected validation subjects. Paired t-tests were used to compare the accuracy of measures obtained between the automated and manual image integration methods.</p><p><strong>Results: </strong>The validation results showed statistically significant differences between the automated and manual methods on the upper lip and soft tissue B point. Otherwise, no statistically significant difference was found.</p><p><strong>Conclusions: </strong>Automated photograph-cephalogram image integration using AI models seemed to be as reliable as manual superimposition procedures.</p>","PeriodicalId":94224,"journal":{"name":"The Angle orthodontist","volume":" ","pages":"595-601"},"PeriodicalIF":0.0000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11493416/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"The Angle orthodontist","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2319/010124-1.1","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Objectives: To develop and evaluate an automated method for combining a digital photograph with a lateral cephalogram.
Materials and methods: A total of 985 digital photographs were collected and soft tissue landmarks were manually detected. Then 2500 lateral cephalograms were collected, and corresponding soft tissue landmarks were manually detected. Using the images and landmark identification information, two different artificial intelligence (AI) models-one for detecting soft tissue on photographs and the other for identifying soft tissue on cephalograms-were developed using different deep-learning algorithms. The digital photographs were rotated, scaled, and shifted to minimize the squared sum of distances between the soft tissue landmarks identified by the two different AI models. As a validation process, eight soft tissue landmarks were selected on digital photographs and lateral cephalometric radiographs from 100 additionally collected validation subjects. Paired t-tests were used to compare the accuracy of measures obtained between the automated and manual image integration methods.
Results: The validation results showed statistically significant differences between the automated and manual methods on the upper lip and soft tissue B point. Otherwise, no statistically significant difference was found.
Conclusions: Automated photograph-cephalogram image integration using AI models seemed to be as reliable as manual superimposition procedures.
目的开发并评估一种将数码照片与头颅侧位图相结合的自动方法:共收集了 985 张数码照片,并人工检测了软组织标志。然后收集了 2500 张侧头颅照片,并人工检测了相应的软组织地标。利用图像和地标识别信息,使用不同的深度学习算法开发了两种不同的人工智能(AI)模型,一种用于检测照片上的软组织,另一种用于识别头颅影像上的软组织。对数字照片进行旋转、缩放和移动,以最小化两种不同人工智能模型所识别的软组织地标之间的距离平方和。作为验证过程,从 100 名额外收集的验证对象的数码照片和头颅侧位X光片上选取了八个软组织地标。采用配对 t 检验来比较自动和手动图像整合方法所获得测量结果的准确性:结果:验证结果表明,在上唇和软组织 B 点上,自动和手动方法的差异具有统计学意义。结论:自动照片-脑电图图像整合方法与人工图像整合方法在上唇和软组织 B 点上的差异具有统计学意义:结论:使用人工智能模型进行自动照片-脑电图图像整合似乎与手动叠加程序一样可靠。