Reproducibility of linear and angular cephalometric measurements obtained by an artificial-intelligence assisted software (WebCeph) in comparison with digital software (AutoCEPH) and manual tracing method

• Published in: Dental press journal of orthodontics Vol. 28; no. 1; p. e2321214
• Main Authors: Prince, S Tsander Tito, Srinivasan, Dilip, Duraisamy, Sangeetha, Kannan, Ravi, Rajaram, Krishnaraj
• Format: Journal Article
• Language: English; Portuguese
• Published: Brazil Dental Press International 2023; Dental Press Editora
• Subjects: Agreements; Artificial Intelligence; Cephalometry; Cephalometry - methods; DENTISTRY, ORAL SURGERY & MEDICINE; Digitization; Humans; Identification; Image Processing, Computer-Assisted - methods; Intelligence; Original; Orthodontics; Reproducibility; Reproducibility of Results; Software; Standard deviation; Statistical analysis; Cephalometry; Ortodontia; Cefalometria; Artificial intelligence; Orthodontics; Inteligência artificial
• ISSN: 2176-9451; 2177-6709; 2177-6709
• DOI: 10.1590/2177-6709.28.1.e2321214.oar

It has been suggested that human errors during manual tracing of linear/angular cephalometric parameters can be eliminated by using computer-aided analysis. The landmarks, however, are located manually and the computer system completes the analysis. With the advent of Artificial Intelligence in the field of Dentistry, automatic location of the landmarks has become a promising tool in digital Orthodontics. Fifty pretreatment lateral cephalograms obtained from the Orthodontic department of SRM dental college (India) were used. Analysis were done by the same investigator using the following methods: WebCeph™, AutoCEPH© for Windows or manual tracing. Landmark identification was carried out automatically by Artificial Intelligence in WebCeph™ and with a mouse driven cursor in AutoCEPH©, and manually using acetate sheet and 0.3-mm pencil, ruler and a protractor. The mean differences of the cephalometric parameters obtained between the three methods were calculated using ANOVA with statistical significance set at p<0.05. Intraclass correlation coefficient (ICC) was used to determine both reproducibility and agreement between linear and angular measurements obtained from the three methods and intrarater reliability of repeated measurements. ICC value of >0.75 indicated good agreement. Intraclass correlation coefficient between the three groups was >0.830, showing good level of agreement, and the value within each group was >0.950, indicating high intrarater reliability. Artificial Intelligence assisted software showed good agreement with AutoCEPH© and manual tracing for all the cephalometric measurements.