Automatic Landmark Annotation and Measurement of 3D Mandibular Morphology Using Non-Rigid Registration: A Preliminary Exploration and Accuracy Assessment
Restricted accessResearch articleFirst published online December, 2025
Automatic Landmark Annotation and Measurement of 3D Mandibular Morphology Using Non-Rigid Registration: A Preliminary Exploration and Accuracy Assessment
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.
Design
Statistical analysis.
Setting
Digital technology center, tertiary hospital.
Participants
130 healthy Chinese adults with equal gender distribution, average age 28.2 ± 5.6 years.
Methods
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.
Main Outcome Measure:
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.
Results
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.
Conclusions
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.
ZhangYSchepartzLA. Three-dimensional geometric morphometric studies of modern human occipital variation. PLoS One. 2021;16(1 January):1-19. doi:https://doi.org/10.1371/journal.pone.0245445
2.
BFL. Principal warps: Thin-plate splines and the decomposition of deformations. IEEE Trans Pattern Anal Mach Intell. 1989;11(6):567.
3.
YoshikawaHTanikawaCItoS, et al.A three-dimensional cephalometric analysis of Japanese adults and its usefulness in orthognathic surgery: A retrospective study. J Cranio-Maxillofacial Surg. 2022;50(4):353-363. doi:https://doi.org/10.1016/j.jcms.2022.02.002
HanMDMominMRMunarettoAMHaoS. Three-dimensional cephalometric analysis of the maxilla: Analysis of new landmarks. Am J Orthod Dentofac Orthop. 2019;156(3):337-344. doi:https://doi.org/10.1016/j.ajodo.2018.09.018
6.
AlmpaniKAdjeiALibertonDKVermaPHungMLeeJS. Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans. J Vis Exp. 2023(199). doi:https://doi.org/10.3791/65224
7.
FagertunJHarderSRosengrenA, et al.3D Facial landmarks: Inter-operator variability of manual annotation. BMC Med Imaging. 2014;14(1):35. doi:https://doi.org/10.1186/1471-2342-14-35
8.
SchwendickeFChaurasiaAArsiwalaL, et al.Deep learning for cephalometric landmark detection: Systematic review and meta-analysis. Clin Oral Investig. 2021;25(7):4299-4309. doi:https://doi.org/10.1007/s00784-021-03990-w
9.
AmbergBRomdhaniSVetterT. Optimal step nonrigid ICP algorithms for surface registration. 2007 IEEE Conference on Computer Vision and Pattern Recognition; 2007; IEEE:1-8. doi:https://doi.org/10.1109/CVPR.2007.383165
10.
AudenaertEAVan HouckeJAlmeidaDF, et al.Cascaded statistical shape model based segmentation of the full lower limb in CT. Comput Methods Biomech Biomed Engin. 2019;22(6):644-657. doi:https://doi.org/10.1080/10255842.2019.1577828
PortoARolfeSMagaAM. ALPACA: A fast and accurate computer vision approach for automated landmarking of three-dimensional biological structures. Methods Ecol Evol. 2021;12(11):2129-2144. doi:https://doi.org/10.1111/2041-210X.13689
13.
GuoJMeiXTangK. Automatic landmark annotation and dense correspondence registration for 3D human facial images. BMC Bioinformatics. 2013;14(1):232. doi:https://doi.org/10.1186/1471-2105-14-232
14.
WenAZhuYXiaoN, et al.Comparison study of extraction accuracy of 3D facial anatomical landmarks based on non-rigid registration of face template. Diagnostics. 2023;13(6):1-16. doi:https://doi.org/10.3390/diagnostics13061086
15.
WhiteJDOrtega-CastrillónAMatthewsH, et al.Meshmonk: Open-source large-scale intensive 3D phenotyping. Sci Rep. 2019;9(1):1-11. doi:https://doi.org/10.1038/s41598-019-42533-y
16.
KlopCBeckingAGKlopC, et al.A three-dimensional statistical shape model of the growing mandible. Sci Rep. 2021;11(1):18843. doi:https://doi.org/10.1038/s41598-021-98421-x
17.
FournierGMaretDTelmonNSavallF. An automated landmark method to describe geometric changes in the human mandible during growth. Arch Oral Biol. 2023;149(January):105663. doi:https://doi.org/10.1016/j.archoralbio.2023.105663
R Core Team. R: A Language and Environment for Statistical Computing. Published online 2021. https://www.r-project.org/
22.
ZouGY. Sample size formulas for estimating intraclass correlation coefficients with precision and assurance. Stat Med. 2012;31(29):3972-3981. doi:https://doi.org/10.1002/sim.5466
23.
VerhelstPJMatthewsHVerstraeteL, et al.Automatic 3D dense phenotyping provides reliable and accurate shape quantification of the human mandible. Sci Rep. 2021;11(1):1-10. doi:https://doi.org/10.1038/s41598-021-88095-w
24.
HermannNVKreiborgSDarvannTAJensenBLDahlEBolundS. Early craniofacial morphology and growth in children with unoperated isolated cleft palate. Cleft Palate-Craniofacial J. 2002;39(6):604-622. doi:https://doi.org/10.1597/1545-1569_2002_039_0604_ecmagi_2.0.co_2
25.
HermannNVDarvannTAErsbøllBKKreiborgS. Short mandible – a possible risk factor for cleft palate with/without a cleft lip. Orthod Craniofac Res. 2014;17(2):106-114. doi:https://doi.org/10.1111/ocr.12036
26.
BoutrosSShetyePRGhaliSCarterCRMcCarthyJGGraysonBH. Morphology and growth of the mandible in Crouzon, Apert, and Pfeiffer syndromes. J Craniofac Surg. 2007;18(1):146-150. doi:https://doi.org/10.1097/01.scs.0000248655.53405.a7
27.
YangYWuYGuY, et al.Alteration of maxillary and mandibular growth of adult patients with unoperated isolated cleft palate. J Craniofac Surg. 2013;24(4):1078-1082. doi:https://doi.org/10.1097/SCS.0b013e318287cac3
28.
DoucetJCHerlinCBigorreMBäumlerCSubsolGCaptierG. Effects of growth on maxillary distraction osteogenesis in cleft lip and palate. J Cranio-Maxillofacial Surg. 2013;41(8):836-841. doi:https://doi.org/10.1016/j.jcms.2013.01.038
29.
SchipperJAMvan LieshoutMJSBöhringerS, et al.Modelling growth curves of the normal infant’s mandible: 3D measurements using computed tomography. Clin Oral Investig. 2021;25(11):6365-6375. doi:https://doi.org/10.1007/s00784-021-03937-1
30.
YoungRMagaAM. Performance of single and multi-atlas based automated landmarking methods compared to expert annotations in volumetric microCT datasets of mouse mandibles. Front Zool. 2015;12(1):33. doi:https://doi.org/10.1186/s12983-015-0127-8
31.
BeslPJMcKayND. A method for registration of 3-D shapes. IEEE Trans Pattern Anal Mach Intell. 1992;14(2):239-256. doi:https://doi.org/10.1109/34.121791
32.
SerafinMBaldiniBCabitzaF, et al.Accuracy of automated 3D cephalometric landmarks by deep learning algorithms: Systematic review and meta-analysis. Radiol Med. 2023;128(5):544-555. doi:https://doi.org/10.1007/s11547-023-01629-2
33.
DengHHLiuQChenA, et al.Clinical feasibility of deep learning-based automatic head CBCT image segmentation and landmark detection in computer-aided surgical simulation for orthognathic surgery. Int J Oral Maxillofac Surg. 2023;52(7):793-800. doi:https://doi.org/10.1016/j.ijom.2022.10.010
34.
YunHSHyunCMBaekSHLeeSHSeoJK. A semi-supervised learning approach for automated 3D cephalometric landmark identification using computed tomography. P.P. Abdul Majeed A, ed. PLoS One. 2022;17(9):e0275114. doi:https://doi.org/10.1371/journal.pone.0275114
35.
ZhangRJieBHeY, et al.Craniomaxillofacial bone segmentation and landmark detection using semantic segmentation networks and an unbiased heatmap. IEEE J Biomed Heal Informatics. Published online 2023:1-11. doi:https://doi.org/10.1109/JBHI.2023.3337546
36.
LagravèreMOLowCFlores-MirC, et al.Intraexaminer and interexaminer reliabilities of landmark identification on digitized lateral cephalograms and formatted 3-dimensional cone-beam computerized tomography images. Am J Orthod Dentofac Orthop. 2010;137(5):598-604. doi:https://doi.org/10.1016/j.ajodo.2008.07.018
37.
ParkJBaumrindSCurrySCarlsonSKBoydRLOhH. Reliability of 3D dental and skeletal landmarks on CBCT images. Angle Orthod. 2019;89(5):758-767. doi:https://doi.org/10.2319/082018-612.1
38.
KimMJLiuYOhSHAhnHWKimSHNelsonG. Automatic cephalometric landmark identification system based on the multi-stage convolutional neural networks with CBCT combination images. Sensors. 2021;21(2):505. doi:https://doi.org/10.3390/s21020505
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
