This study aims to determine the utility of 3D photography for evaluating the severity of metopic craniosynostosis (MCS) using a validated, supervised machine learning (ML) algorithm.
Design/Setting/Patients
This single-center retrospective cohort study included patients who were evaluated at our tertiary care center for MCS from 2016 to 2020 and underwent both head CT and 3D photography within a 2-month period.
Main Outcome Measures
The analysis method builds on our previously established ML algorithm for evaluating MCS severity using skull shape from CT scans. In this study, we regress the model to analyze 3D photographs and correlate the severity scores from both imaging modalities.
Results
14 patients met inclusion criteria, 64.3% male (n = 9). The mean age in years at 3D photography and CT imaging was 0.97 and 0.94, respectively. Ten patient images were obtained preoperatively, and 4 patients did not require surgery. The severity prediction of the ML algorithm correlates closely when comparing the 3D photographs to CT bone data (Spearman correlation coefficient [SCC] r = 0.75; Pearson correlation coefficient [PCC] r = 0.82).
Conclusion
The results of this study show that 3D photography is a valid alternative to CT for evaluation of head shape in MCS. Its use will provide an objective, quantifiable means of assessing outcomes in a rigorous manner while decreasing radiation exposure in this patient population.
van der MeulenJ. Metopic synostosis. Childs Nerv Syst. 2012;28(9):1359–1367.
2.
CornelissenMOttelanderBRizopoulosDvan der HulstRMink van der MolenAvan der HorstCDelyeHvan VeelenMLBonselGMathijssenI. Increase of prevalence of craniosynostosis. J Craniomaxillofac Surg. 2016;44(9):1273–1279.
3.
Di RoccoFArnaudERenierD. Evolution in the frequency of nonsyndromic craniosynostosis. J Neurosurg Pediatr. 2009;4(1):21–25.
4.
van der MeulenJvan der HulstRvan AdrichemLArnaudEChin-ShongDDuncanCHabetsEHinojosaJMathijssenIMayP, et al.The increase of metopic synostosis: a pan-European observation. J Craniofac Surg. 2009;20(2):283–286.
5.
BrennerDEllistonCHallEBerdonW. Estimated risks of radiation-induced fatal cancer from pediatric CT. AJR Am J Roentgenol. 2001;176(2):289–296.
6.
AhammoutCPerezFABirgfeldCBKoudstaalMJEllenbogenRGLeeAHeikeCL. Evaluating the utility of routine computed tomography scans after cranial vault reconstruction for children with craniosynostosis. Plast Reconstr Surg. 2021;148(1):63e–70e.
7.
BruceMKMittalAMWhittDSFlomLLPfaffMJLoseeJEGoldsteinJA. Computed tomography associated radiation exposure in children with craniosynostosis. Childs Nerv Syst. 2021;37(8):2635–2641.
8.
BinningMRagelBBrockmeyerDLWalkerMLKestleJR. Evaluation of the necessity of postoperative imaging after craniosynostosis surgery. J Neurosurg. 2007;107(1 Suppl):43–45.
9.
MortonRPReynoldsRMRamakrishnaRLevittMRHopperRALeeABrowdSR. Low-dose head computed tomography in children: a single institutional experience in pediatric radiation risk reduction: clinical article. J Neurosurg Pediatr. 2013;12(4):406–410.
10.
MontoyaJCEckelLJDeLoneDRKotsenasALDiehnFEYuLBartleyACCarterREMcColloughCHFletcherJG. Low-Dose CT for craniosynostosis: preserving diagnostic benefit with substantial radiation dose reduction. AJNR Am J Neuroradiol. 2017;38(4):672–677.
11.
HoOASaberNStephensDClausenADrakeJForrestCPhillipsJ. Comparing the Use of 3D photogrammetry and computed tomography in assessing the severity of single-suture nonsyndromic craniosynostosis. Plast Surg (Oakv). 2017;25(2):78–83.
12.
MeulsteeJWVerhammeLMBorstlapWAVan der HeijdenFDe JongGAXiTBergéSJDelyeHMaalTJJ. A new method for three-dimensional evaluation of the cranial shape and the automatic identification of craniosynostosis using 3D stereophotogrammetry. Int J Oral Maxillofac Surg. 2017;46(7):819–826.
13.
de JongGBijlsmaEMeulsteeJWennenMvan LindertEMaalTAquariusRDelyeH. Combining deep learning with 3D stereophotogrammetry for craniosynostosis diagnosis. Sci Rep. 2020;10(1):15346.
14.
RasFHabetsLLvan GinkelFCPrahl-AndersenB. Quantification of facial morphology using stereophotogrammetry--demonstration of a new concept. J Dent. 1996;24(5):369–374.
15.
PlooijJMSwennenGRRangelFAMaalTJSchutyserFABronkhorstEMKuijpers-JagtmanAMBergéSJ. Evaluation of reproducibility and reliability of 3D soft tissue analysis using 3D stereophotogrammetry. Int J Oral Maxillofac Surg. 2009;38(3):267–273.
16.
FourieZDamstraJGerritsPORenY. Evaluation of anthropometric accuracy and reliability using different three-dimensional scanning systems. Forensic Sci Int. 2011;207(1–3):127–134.
17.
ZhaoZXieLCaoDIzadikhahIGaoPZhaoYYanB. Accuracy of three-dimensional photogrammetry and cone beam computed tomography based on linear measurements in patients with facial deformities. Dentomaxillofac Radiol. 2021;50(2):20200001.
18.
MetzgerTEKulaKSEckertGJGhoneimaAA. Orthodontic soft-tissue parameters: a comparison of cone-beam computed tomography and the 3dMD imaging system. Am J Orthod Dentofacial Orthop. 2013;144(5):672–681.
19.
MaalTJJPlooijJMRangelFAMollemansWSchutyserFACBergéSJ. The accuracy of matching three-dimensional photographs with skin surfaces derived from cone-beam computed tomography. International Journal of Oral & Maxillofacial Surgery. 2008;37(7):641–646.
20.
KhambayBNebelJ-CBowmanJWalkerFHadleyDMAyoubA. 3D Stereophotogrammetric image superimposition onto 3D CT scan images: the future of orthognathic surgery. A pilot study. Int J Adult Orthodon Orthognath Surg. 2002;17(4):331.
21.
LittlefieldTRKellyKMCherneyJCBealsSPPomattoJK. Development of a new three-dimensional cranial imaging system. J Craniofac Surg. 2004;15(1):175–181.
22.
WongJYOhAKOhtaEHuntATRogersGFMullikenJBDeutschCK. Validity and reliability of craniofacial anthropometric measurement of 3D digital photogrammetric images. Cleft Palate Craniofac J. 2008;45(3):232–239.
23.
McKayDRDavidgeKMWilliamsSKEllisLAChongDKTeixeiraRPGreensmithALHolmesAD. Measuring cranial vault volume With three-dimensional photography: a method of measurement comparable to the gold standard. Journal of Craniofacial Surgery. 2010;21(5):1419–1422.
24.
SchaafHPons-KuehnemannJMalikCStreckbeinPPreussMHowaldtH-PWilbrandJ-F. Accuracy of three-dimensional photogrammetric images in non-synostotic cranial deformities. Neuropediatrics. 2010;41(01):24–29.
25.
WilbrandJFSzczukowskiABlecherJCPons-KuehnemannJChristophisPHowaldtHPSchaafH. Objectification of cranial vault correction for craniosynostosis by three-dimensional photography. J Craniomaxillofac Surg. 2012;40(8):726–730.
26.
AkanBVeliİ. Evaluation of soft-tissue changes in young adults treated with the forsus fatigue-resistant device. Am J Orthod Dentofacial Orthop. 2020;157(4):481–489.e482.
27.
BüyükçavuşMHFindikYBaykulT. Evaluation of changes in nasal projection after surgically assisted rapid maxillary expansion With 3dMD face system. J Craniofac Surg. 2020;31(5):e462–e465.
28.
TuLPorrasAROhALeporeNMastromanolisMTseringDPaniaguaBEnquobahrieAKeatingRRogersGF,et al.Radiation-free quantification of head malformations in craniosynostosis patients from 3D photography. Proc SPIE Int Soc Opt Eng. 2018;10575:105751U.
29.
PorrasARTuLTseringDMantillaEOhAEnquobahrieAKeatingRRogersGFLinguraruMG. Quantification of head shape from three-dimensional photography for presurgical and postsurgical evaluation of craniosynostosis. Plast Reconstr Surg. 2019;144(6):1051e–1060e.
30.
ChoMJHallacRREffendiMSeawardJRKaneAA. Comparison of an unsupervised machine learning algorithm and surgeon diagnosis in the clinical differentiation of metopic craniosynostosis and benign metopic ridge. Sci Rep. 2018;8(1):6312.
31.
BhalodiaRDvoracekLAAyyashAMKavanLWhitakerRGoldsteinJA. Quantifying the severity of metopic craniosynostosis: a pilot study application of machine learning in craniofacial surgery. Journal of Craniofacial Surgery. 2020;31(3):697–701.
32.
OtsuN. “A threshold selection method from gray-level histograms.” IEEE transactions on systems. Man, and Cybernetics. 1979;9(1):62–66.
33.
WoldSEsbensenKGeladiP. Principal component analysis. Chemom Intell Lab Syst. 1987;2(1–3):37–52.
34.
JolliffeIT. A note on the Use of principal components in regression. Journal of the Royal Statistical Society: Series C (Applied Statistics). 1982;31(3):300–303.
35.
UebersaxJSGroveWM. A latent trait finite mixture model for the analysis of rating agreement. Biometrics. 1993;49(3):823–835.
36.
MuthénBMuthénBO. Statistical analysis with latent variables. New York: Wiley; 2009.
37.
JunnADinisJHaucSCBruceMKParkKETaoWChristensenCWhitakerRGoldsteinJAAlperovichM. “Validation of artificial intelligence severity assessment in metopic craniosynostosis”. Cleft Palate Craniofac J. 2021:Epub ahead of print.
38.
LeMBPatelKSkolnickGNaidooSSmythMKaneAWooAS. Assessing long-term outcomes of open and endoscopic sagittal synostosis reconstruction using three-dimensional photography. J Craniofac Surg. 2014;25(2):573–576.
39.
EleyKAWatt-SmithSRSheerinFGoldingSJ. “Black bone” MRI: a potential alternative to CT with three-dimensional reconstruction of the craniofacial skeleton in the diagnosis of craniosynostosis. Eur Radiol. 2014;24(10):2417–2426.
40.
SaarikkoAMellanenEKuuselaLLeikolaJKarppinenAAuttiTVirtanenPBrandstackN. Comparison of black bone MRI and 3D-CT in the preoperative evaluation of patients with craniosynostosis. J Plast Reconstr Aesthet Surg. 2020;73(4):723–731.
