Precision of cephalometric analysisviafully and semiautomatic evaluation of digital lateral cephalographs

The use and performance of artificial intelligence applications in dental and maxillofacial radiology: A systematic review

OBJECTIVES

To investigate the current clinical applications and diagnostic performance of artificial intelligence (AI) in dental and maxillofacial radiology (DMFR).

METHODS

Studies using applications related to DMFR to develop or implement AI models were sought by searching five electronic databases and four selected core journals in the field of DMFR. The customized assessment criteria based on QUADAS-2 were adapted for quality analysis of the studies included.

RESULTS

The initial electronic search yielded 1862 titles, and 50 studies were eventually included. Most studies focused on AI applications for an automated localization of cephalometric landmarks, diagnosis of osteoporosis, classification/segmentation of maxillofacial cysts and/or tumors, and identification of periodontitis/periapical disease. The performance of AI models varies among different algorithms.

CONCLUSION

The AI models proposed in the studies included exhibited wide clinical applications in DMFR. Nevertheless, it is still necessary to further verify the reliability and applicability of the AI models prior to transferring these models into clinical practice.

Reliability Assessment of Orthodontic Apps for Cephalometrics

Objective

The aim of this study was to evaluate the accuracy and reliability of cephalometric measurements using iPad apps called CephNinja and SmartCeph Pro. The measurements were compared with the measurements obtained using Dolphin Imaging computer software.

Methods

Twenty digital cephalometric radiographs were randomly selected from the archives and traced using the CephNinja app, SmartCeph Pro app, and Dolphin Imaging software. Twenty-one landmarks and 16 measurements were performed in each program. The statistical analysis was conducted using the Bland-Altman analysis at a significance level of 0.05.

Results

For the CephNinja app, there were seven measurements that were in accordance with Dolphin Imaging software. For the SmartCeph Pro app, six measurements were in accordance with Dolphin software. Both apps gave better results for angular measurements than linear ones.

Conclusion

These findings indicate that, although they are user-friendly, orthodontic apps for cephalometrics are not equal with Dolphin software now and need to be developed to be more reliable for most of the measurements.

Reliability of skeletal maturity analysis using the cervical vertebrae maturation method on dedicated software

OBJECTIVES

The aim of this study was to assess the feasibility of skeletal maturation analysis using the Cervical Vertebrae Maturation (CVM) method by means of dedicated software, developed in collaboration with Outside Format (Paullo-Milan), as compared with manual analysis.

MATERIALS AND METHODS

From a sample of patients aged 7-21 years, we gathered 100 lateral cephalograms, 20 for each of the five CVM stages. For each cephalogram, we traced cervical vertebrae C2, C3 and C4 by hand using a lead pencil and an acetate sheet and dedicated software. All the tracings were made by an experienced operator (a dentofacial orthopedics resident) and by an inexperienced operator (a student in dental surgery). Each operator recorded the time needed to make each tracing in order to demonstrate differences in the times taken.

RESULTS

Concordance between the manual analysis and the analysis performed using the dedicated software was 94% for the resident and 93% for the student. Interobserver concordance was 99%. The hand-tracing was quicker than that performed by means of the software (28 seconds more on average).

CONCLUSIONS

The cervical vertebrae analysis software offers excellent clinical performance, even if the method takes longer than the manual technique.

Reliability and the smallest detectable differences of lateral cephalometric measurements

INTRODUCTION

The aim of this study was to determine the reliability and the measuring error (by means of the smallest detectable error) of 11 angular and 4 linear measurements commonly used for cephalometric analysis.

METHODS

Twenty-five digital lateral cephalograms were randomly selected and traced with Viewbox software (version 3.1.1.13, dHAL Software, Kifissia, Greece). This was repeated 3 times by 2 observers during 3 sessions. There was at least 1 week between each session. Differences were analyzed with a repeated measurement analysis of variance (ANOVA). Intraobserver and interobserver reliabilities were calculated with intraclass correlation coefficients (ICC) based on absolute agreement. Measurement error was determined by means of the smallest detectable difference.

RESULTS

The intraobserver agreement of the measurements was good (ICC >0.82). SNA, SNB, ANB, and ANS-Me had the smallest intraobserver errors for both observers (>1.86 mm or degrees). Except for SN-FH (ICC = 0.76), interobserver agreement was good (ICC >0.87).

CONCLUSIONS

Determining the appropriate measuring error of cephalometric measurements by means of the smallest detectable difference is necessary to find the true difference between the start and the end of active treatment. Depending on the magnitude of clinical significance, the measuring error was possibly clinically significant for all variables tested and, therefore, questions the use of these variables to detect the true treatment effect.