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

Comparison Between an Expert Operator an Inexperienced Operator, and Artificial Intelligence Software: A Brief Clinical Study of Cephalometric Diagnostic

INTRODUCTION

Artificial intelligence (AI) is constantly developing in several medical areas and has become useful to assist with treatment planning. Orthodontics and maxillofacial surgery use AI-based technology to identify and select cephalometric points for diagnostics. Although some studies have shown promising results from the use of AI, the evidence is still limited. Hence, additional investigation is justified.

MATERIALS AND METHODS

In this retrospective study, 2 human operators (1 expert and 1 inexperienced) and 1 software analyzed 30 lateral cephalograms of individuals with orthodontic treatment indications. They measured 10 cephalometric variables and then 2 weeks later, repeated measurements on 30% of the sample. We evaluated the reliability of the measurements between the 2-time points and the differences in the means between the expert operator and the AI software and between the expert and inexperienced operators.

RESULTS

There was high reliability for the expert operator and AI measurements, and moderate reliability for the inexperienced operator measurements. There were some significant differences in the means produced by the AI software and the inexperienced operator compared with the expert operator.

CONCLUSION

Although AI is useful for cephalometric analysis, it should be used with caution because there are differences compared with analysis by humans.

Comparison of Three Commercially Available, AI-Driven Cephalometric Analysis Tools in Orthodontics

Background: Cephalometric analysis (CA) is an indispensable diagnostic tool in orthodontics for treatment planning and outcome assessment. Manual CA is time-consuming and prone to variability. Methods: This study aims to compare the accuracy and repeatability of CA results among three commercial AI-driven programs: CephX, WebCeph, and AudaxCeph. This study involved a retrospective analysis of lateral cephalograms from a single orthodontic center. Automated CA was performed using the AI programs, focusing on common parameters defined by Downs, Ricketts, and Steiner. Repeatability was tested through 50 randomly reanalyzed cases by each software. Statistical analyses included intraclass correlation coefficients (ICC3) for agreement and the Friedman test for concordance. Results: One hundred twenty-four cephalograms were analyzed. High agreement between the AI systems was noted for most parameters (ICC3 > 0.9). Notable differences were found in the measurements of angle convexity and the occlusal plane, where discrepancies suggested different methodologies among the programs. Some analyses presented high variability in the results, indicating errors. Repeatability analysis revealed perfect agreement within each program. Conclusions: AI-driven cephalometric analysis tools demonstrate a high potential for reliable and efficient orthodontic assessments, with substantial agreement in repeated analyses. Despite this, the observed discrepancies and high variability in part of analyses underscore the need for standardization across AI platforms and the critical evaluation of automated results by clinicians, particularly in parameters with significant treatment implications.

Digital versus Manual Tracing in Cephalometric Analysis: A Systematic Review and Meta-Analysis

Background: Over the years, various researchers have attempted to compare digital cephalometry with the conventional manual approach. There is a need to comprehensively analyze the findings from the earlier studies and determine the potential advantages and limitations of each method. The present systematic review aimed to compare the accuracy of digital and manual tracing in cephalometric analysis for the identification of skeletal and dental landmarks. Methods: A systematic search was performed using the keywords "Digital" AND "Manual" AND "Cephalometry" to identify relevant studies published in the English language in the past decade. The electronic data resources consulted for the elaborate search included the Cochrane Central Register of Controlled Trials (CENTRAL), MEDLINE, CINAHL, EMBASE, PsycINFO, Scopus, ERIC, and ScienceDirect with controlled vocabulary and free text terms. Results: A total of n = 20 studies were identified that fulfilled the inclusion and exclusion criteria within the timeframe of 2013 to 2023. The data extracted from the included articles and corresponding meta-analyses are presented in the text. Conclusions: The findings of the present systematic review and meta-analysis revealed trends suggesting that digital tracing may offer reliable measurements for specific cephalometric parameters efficiently and accurately. Orthodontists must consider the potential benefits of digital cephalometry, including time-saving and user-friendliness.

A comparative evaluation of concordance and speed between smartphone app-based and artificial intelligence web-based cephalometric tracing software with the manual tracing method: A cross-sectional study

Background

This study compared the accuracy and speed of cephalometric analysis using an artificial intelligence web-based method and a smartphone app-based system with manual cephalometric analysis as the reference standard.

Material and Methods

In this cross-sectional study, the lateral cephalograms were analysed using four methods: manual tracing, smartphone app tracing, artificial intelligence web-based automated tracing without manual landmark identification correction and artificial intelligence web-based automated tracing with manual landmark identification correction. The principal investigator obtained linear and angular cephalometric measurements to compare the accuracies of the four methods being assessed. Additionally, the duration required for landmark identification and subsequent analysis was recorded.

Results

The analyses included 40 lateral cephalograms that were selected based on the inclusion and exclusion criteria. Very good to excellent agreement was observed in the accuracies of the artificial intelligence web-based and smartphone app-based systems compared with manual tracing (interclass correlation coefficient values ranging from 0.707 to 0.9, p< 0.001). Of the artificial intelligence web-based systems, the method without correction of automated landmark detection showed less reliable measurements than the other methods. Cephalometric analysis using artificial intelligence web-based and smartphone app-based systems consumed less time than manual tracing (p< 0.001).

Conclusions

Artificial intelligence web-based automated tracing with manual landmark identification correction and smartphone-based app provide results that are comparable to those from the manual tracing method. However, artificial intelligence web-based systems require improvements in terms of automated landmark identification to obtain results that are similar to those from the other methods being assessed. Key words:Artificial Intelligence, Cephalometry, Computer software, Mobile application.