Is automatic cephalometric software using artificial intelligence better than orthodontist experts in landmark identification?

Abstract

Background: To evaluate the techniques used for the automatic digitization of cephalograms using artificial intelligence algorithms, highlighting the strengths and weaknesses of each one and reviewing the percentage of success in localizing each cephalometric point.

Methods: Lateral cephalograms were digitized and traced by three calibrated senior orthodontic residents with or without artificial intelligence (AI) assistance. The same radiographs of 43 patients were uploaded to AI-based machine learning programs MyOrthoX, Angelalign, and Digident. Image J was used to extract x- and y-coordinates for 32 cephalometric points: 11 soft tissue landmarks and 21 hard tissue landmarks. The mean radical errors (MRE) were assessed radical to the threshold of 1.0 mm,1.5 mm, and 2 mm to compare the successful detection rate (SDR). One-way ANOVA analysis at a significance level of P < .05 was used to compare MRE and SDR. The SPSS (IBM-vs. 27.0) and PRISM (GraphPad-vs.8.0.2) software were used for the data analysis.

Results: Experimental results showed that three methods were able to achieve detection rates greater than 85% using the 2 mm precision threshold, which is the acceptable range in clinical practice. The Angelalign group even achieved a detection rate greater than 78.08% using the 1.0 mm threshold. A marked difference in time was found between the AI-assisted group and the manual group due to heterogeneity in the performance of techniques to detect the same landmark.

Conclusions: AI assistance may increase efficiency without compromising accuracy with cephalometric tracings in routine clinical practice and research settings.

Keywords: Artificial intelligence; Automatic digitization; Cephalometric tracings.

Fig. 1

The 32 anatomical landmarks used in this challenge. All landmarks are defined and explained in Table 1

Fig. 2

Cephalometric tracing of anatomical structures in three AI-assisted programs. Sample lateral cephalometric radiograph with a 30-mm ruler uploaded to the MyOrthoX, Angelalign, and Digident programs

Fig. 3

Mean radical error (MRE) for each landmark measured by three AI-assisted programs

Fig. 4

Mean radical error (MRE) for all Landmarks measured by three AI-assisted programs. One-way ANOVA analysis was applied to compare the MRE among the groups

Fig. 5

Comparison among the three AI-assisted groups in terms of the successful detection rate (SDR). One-way ANOVA analysis was applied to compare the average SDR among the groups within 1.0, 1.5, and 2.0 mm thresholds. Statistical significance was set at a p-value < 0.05

Fig. 6

Mean time needed for landmark detection for the manual group, AI group, and AI-assisted group. Paired t-test was conducted to compare the average time for cephalometric analysis between AI-assistant groups (MyOrthoX-assisted, Angelalign-assisted, and Digident-assisted) and manual groups. Statistical significance was set at a p-value < 0.05