الفهرس 
Review of LiteratureOnly 14 pages are availabe for public view
 |  | from | 101 |  |  |
| | | from | 101 | | |
Abstract
This study aimed to assess the reliability of lateral cephalometric analysis performed by an AI- dependant software program (AudaxCeph®).
One Hundred and Eighty digital cephalometric radiographs acquired by Vatech PaX-i X-ray machine, were used in the study. The anatomical landmarks of both Steiner and McNamara analyses were manually traced using a third-party software AudaxCeph® Empower, version 6.6.12.4731 (Audax d.o.o., Ljubljana, Slovenia), the tracing was performed by two radiologists with more than five years of experience in digital cephalometry to determine the inter-observer reliability, then it was repeated with an interval of two weeks to determine the intra-observer reliability. The landmarks were retraced automatically through the fully automatic option on the same software program using convolutional neural network.
Regarding McNamara analysis, Interobserver and intra-observer reliability revealed excellent reliability (ICC > 0.9). the results of this study showed excellent reliability of the artificial intelligence measurements compared to the manual measurements, with an interclass correlation coefficient >0.9.
Regarding Steiner analysis, Interobserver reliability revealed excellent reliability (1>ICC > 0.75) of all measurements except for Angle SNB degree, ANB degree, Positive 1/NA degree, Positive 1/SN degree, Negative 1/ NB degree and Pg/NB mm which showed moderate reliability (0.4>ICC>0.74). Intra-observer reliability revealed excellent reliability (ICC > 0.9). Our results showed excellent reliability of the artificial intelligence measurements compared to the manual measurements (0.75<ICC<1 excluding Positive 1/SN degree, Negative 1i/NB mm, Pg/NB mm, and S-L point mm, which show moderate reliability with 0.4<ICC<0.74). Two measurements showed poor reliability (Holdaway ratio and S-E point mm).