{"title":"Comparative study of two software for the detection of cephalometric landmarks by artificial intelligence","authors":"Matthieu Moreno, Sarah Gebeile-Chauty","doi":"10.1684/orthodfr.2022.73","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Manual, tedious cephalometric analyzes of a lack of productivity (errors in plotting and measurement) making the prospect of a fully automated algorithm turning out attractive. The objectives of the study were to evaluate the positioning (accuracy and precision) of common landmarks by two software programs offering detection by artificial intelligence (WebCeph™ and DentaliQ®) compared to a manual reference and then to the comparators.</p><p><strong>Materials and methods: </strong>68 lateral cephalograms were selected, 22 landmarks were distributed manually and then the differences between this gold standard and the points detected by each software were measured, as well as the success detection rate (SDR). Statistical analysis was carried out by “confidence ellipses” and two-tailed t-test (p-value of 5%).</p><p><strong>Results: </strong>In terms of accuracy, WebCeph™ and DentaliQ® show a 2 mm SDR of 57.2% and 66.5% respectively. In terms of trueness, the best results are obtained for S, Na and the incisal edges. Large random errors are found for the points Po, So, ENA, ENP, Ba and Go. Other points like Pog and B show a large vertical dispersion. Overall, a slight advantage goes to DentaliQ® even if the difference is not significant.</p><p><strong>Discussion: </strong>The detection precision still seems insufficient for an utilization without human supervision. The results are promising on the detection of certain points. The artificial intelligence saves time for the clinician but the change of positioning of points should still be possible.</p><p><strong>Conclusion: </strong>Advances are rapid and will probably be soon for an effective clinical use.</p>","PeriodicalId":35927,"journal":{"name":"L'' Orthodontie française","volume":"93 1","pages":"41-61"},"PeriodicalIF":0.0000,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"L'' Orthodontie française","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1684/orthodfr.2022.73","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 2
Abstract
Introduction: Manual, tedious cephalometric analyzes of a lack of productivity (errors in plotting and measurement) making the prospect of a fully automated algorithm turning out attractive. The objectives of the study were to evaluate the positioning (accuracy and precision) of common landmarks by two software programs offering detection by artificial intelligence (WebCeph™ and DentaliQ®) compared to a manual reference and then to the comparators.
Materials and methods: 68 lateral cephalograms were selected, 22 landmarks were distributed manually and then the differences between this gold standard and the points detected by each software were measured, as well as the success detection rate (SDR). Statistical analysis was carried out by “confidence ellipses” and two-tailed t-test (p-value of 5%).
Results: In terms of accuracy, WebCeph™ and DentaliQ® show a 2 mm SDR of 57.2% and 66.5% respectively. In terms of trueness, the best results are obtained for S, Na and the incisal edges. Large random errors are found for the points Po, So, ENA, ENP, Ba and Go. Other points like Pog and B show a large vertical dispersion. Overall, a slight advantage goes to DentaliQ® even if the difference is not significant.
Discussion: The detection precision still seems insufficient for an utilization without human supervision. The results are promising on the detection of certain points. The artificial intelligence saves time for the clinician but the change of positioning of points should still be possible.
Conclusion: Advances are rapid and will probably be soon for an effective clinical use.
简介:手工，繁琐的头测量分析缺乏生产力(错误的绘图和测量)，使一个完全自动化的算法的前景变得有吸引力。本研究的目的是通过两个提供人工智能检测的软件程序(WebCeph™和DentaliQ®)评估常见地标的定位(准确性和精密度)，并将其与手动参考和比较器进行比较。材料和方法:选择68张侧位头颅图，人工分配22个地标，然后测量该金标准与各软件检测点的差异，以及成功检测率(SDR)。统计分析采用“置信椭圆”和双尾t检验(p值为5%)。结果:准确度方面，WebCeph™和DentaliQ®的2 mm SDR分别为57.2%和66.5%。在正确率方面，S、Na和切边效果最好。Po, So, ENA, ENP, Ba和Go点存在较大的随机误差。其他点如Pog和B显示出较大的垂直分散。总体而言，DentaliQ®具有轻微的优势，即使差异并不显著。讨论:在没有人工监督的情况下，检测精度似乎还不够。这些结果在某些点的检测上是有希望的。人工智能为临床医生节省了时间，但仍然可以改变穴位的位置。结论:该研究进展迅速，有望在不久的将来获得临床有效应用。
期刊介绍：
L’Orthodontie Française, organe officiel de communication de la Société Française d’Orthopédie Dento-Faciale, est un journal scientifique de référence depuis 1921, de diffusion internationale, indexé à Medline et référencé à l’Index Medicus et à Bibliodent. Le journal a pour vocation d’accueillir les travaux des membres de la SFODF, des conférenciers ayant communiqué lors des congrès de la Société, ou de tout travail soumis à l’approbation de son comité de rédaction, traitant de l’orthopédie dento-faciale ou de tout sujet en rapport avec cette discipline.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
