Left-Right Consistency and Quantification of Craniofacial Asymmetry by Two Fully Automatic AI-Powered Three-Dimensional Cephalometry Systems on CBCT.
AI system Diagnocat showed poor accuracy for gonial angle vs manual tracing
Left-Right Consistency and Quantification of Craniofacial Asymmetry by Two Fully Automatic AI-Powered Three-Dimensional Cephalometry Systems on CBCT.
Automatic three-dimensional (3D) cephalometry on cone beam computed tomography (cone beam computed tomography) is increasingly used in orthodontic and orthognathic practice, but whether fully automatic systems reproduce bilateral measurements with equal fidelity on both sides, and whether the right-left difference they report can be trusted as a clinical measure of asymmetry, has not been studied systematically.
This study aimed to quantify side-specific agreement and asymmetry quantification fidelity of two commercial AI cephalometry systems against calibrated manual 3D tracing.
Thirty-one cone beam computed tomography scans were analysed by calibrated manual tracing (InVivo software), an integrated AI module (AI InVivo), and a cloud-based system (Diagnocat).
Diagnocat's gonial angle readings barely tracked manual tracing at all
Per-side agreement closely mirrored overall accuracy; any systematic error was applied almost equally to both sides (bias difference ≤0.3° or ≤0.9 mm between sides).
The mandibular plane angle achieved excellent ICC (0.95-0.97) and equivalence on both sides for both systems.
Asymmetry agreement was generally weaker than per-side accuracy.
Both systems under-detected clinically relevant gonial asymmetry (sensitivity 0.00-0.17), with errors predominantly in the false-negative direction.
Fully automatic AI-powered 3D cephalometry applies systematic errors symmetrically to both sides, so per-side accuracy holds equally for right and left measurements.
However, asymmetry fidelity is a separate, more demanding property that does not follow from absolute accuracy and remains unreliable for landmark-sensitive parameters such as the gonial angle.
Clinician verification is required before automatic analysis is used for asymmetry assessment.