Artificial intelligence-based cephalometric landmark annotation and measurements according to Arnett’s analysis: can we trust a bot to do that?

Abstract

Objective: To assess the reliability of CEFBOT, an artificial intelligence (AI)-based cephalometry software, for cephalometric landmark annotation and linear and angular measurement according to Arnett’s analysis. Methods: Thirty lateral cephalometric radiographs acquired with a Carestream CS 9000 3D unit (Carestream Health Inc., Rochester/NY) were used in this study. The 66 landmarks and the ten selected linear and angular measurements of Arnett’s analysis were identified on each radiograph by a trained human examiner (control) and by CEFBOT (RadioMemory Ltd., Belo Horizonte, Brazil). For both methods, landmark annotations and measurements were duplicated with an interval of 15 days between measurements and the intraclass correlation coefficient (ICC) was calculated to determine reliability. The numerical values obtained with the two methods were compared by a t-test for independent variables. Results: CEFBOT was able to perform all but one of the ten measurements. ICC values > 0.94 were found for the remaining eight measurements, while the Frankfurt horizontal plane - true horizontal line (THL) angular measurement showed the lowest reproducibility (human, ICC = 0.876; CEFBOT, ICC = 0.768). Measurements performed by the human examiner and by CEFBOT were not statistically different. Conclusion: Within the limitations of our methodology, we concluded that the AI contained in the CEFBOT software can be considered a promising tool for enhancing the capacities of human Radiologists.

Evaluation of fully automated cephalometric measurements obtained from web-based artificial intelligence driven platform

“…While, Silva et al [ 14 ] compared 10 cephalometric measurements of Arnett’s analysis obtained from manual tracing method and CEFBOT; an artificial intelligence (AI) based cephalometric software. They found that measurements obtained from two methods were not statistically different.…”

“…Informed consent was obtained from all the subjects and/or their legal guardians(s). Calculation of sample size was done based on previous studies by Alqahtani [ 12 ] and Silva et al [ 14 ]. A total of 30 pretreatment lateral cephalograms of patients (8 males, 22 females, mean age: 20.17 ± 6.72 years) meeting the inclusion criteria were randomly selected from the archive of Department of Orthodontics, Dhulikhel Hospital.…”

“…Since landmark identification is one of the major sources of error in cephalometric analysis, it is essential to evaluate the accuracy of cephalometric measurements obtained through automatic landmark detection feature of commercially available fully automated cephalometric analysis software like CephX®, CEFBOT, WebCeph™, etc. Recently, few authors have evaluated the accuracy of web-based fully automated cephalometric analysis software CephX® and CEFBOT [ 12 – 14 ]. However, we could not find any published study evaluating the cephalometric measurements obtained from “WebCeph”™.…”

Effect of Artificial Intelligence versus guided Landmarks identification on the accuracy of the Lateral Cephalometric Analysis

“…The mean differences range from 0.2° to 2.9° for angular measurements except Gonial angle 4.55°, Upper 1 to NA angle 3.78° and IMPA 3.72° and from 0.25 to 1.67 mm for linear measurements would probably not make a difference in the treatment and is insignificant for a clinical decision (9,3) .This result was similar to that of Felix Kunz et al (8) which has a very high correlation between the predictions of the AI and the humans' gold standard. Silva et al (14) showed CEFBOT (an artificial intelligence (AI)-based cephalometry software)…”

Use of Advanced Artificial Intelligence in Forensic Medicine, Forensic Anthropology and Clinical Anatomy

“…Automatized 3D cephalometric landmark annotation [41][42][43][44][45][46][47][48][49][50][51][52][53][54][55][56][57][58]…”