Automatic Landmark Annotation and Measurement of 3D Mandibular Morphology Using Non-Rigid Registration: A Preliminary Exploration and Accuracy Assessment.

Abstract

This study aimed to develop an automatic methodology for mandibular landmarking and measurement using non-rigid registration as well as analyze the accuracy of automatic landmarking and measurements.

Statistical analysis.

Digital technology center, tertiary hospital.

130 healthy Chinese adults with equal gender distribution, average age 28.2 ± 5.6 years.

Four mean shape mesh templates were generated from 100 head CT scans. Following manual indication of landmarks, these templates were applied for automatic landmark annotation and measurements on mandibles from another 30 head CT scans, using non-rigid iterative closest point registration.

Differences of landmark coordinates and measurements between automatic and manual annotation were analyzed using mean difference, centroid size, Euclidean distances and intraclass correlation coefficient (ICC), assessing the accuracy and validity of automatic landmark annotation.

The majority of automatic landmarks (16/22) did not exhibit consistent displacement to specific direction. ICCs of all landmark coordinates exceed 0.950, with 87.9% larger than 0.990. The average Euclidean distance between manual and automatic landmarks was 2.038 ± 0.947 mm. Most ICCs of linear and angular measurements between manual and automatic annotation (20/26) exceeded 0.900, with the average errors being 1.425 ± 0.973 mm and 2.257 ± 0.649 °, respectively.

A novel and efficient method for automatic landmark annotation was established based on non-rigid registration. Its credibility and accuracy in mandibular annotation and measurements were demonstrated.