3D Photography to Quantify the Severity of Metopic Craniosynostosis - PubMed (original) (raw)

3D Photography to Quantify the Severity of Metopic Craniosynostosis

Madeleine K Bruce et al. Cleft Palate Craniofac J. 2023 Aug.

Abstract

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.

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.

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.

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).

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.

Keywords: anatomy; computerized tomography; craniofacial morphology; dysmorphology; synostosis.

PubMed Disclaimer

Conflict of interest statement

Disclosures: The authors report no conflict of interest concerning the materials or methods used in this study or the findings specified in this paper.

Figures

Figure 1:

Left: segmenting of CT scans using the Otsu threshold for skin segmentation.31 Middle: cropping at the nasion-porion plane of the CT (upper) and 3D photograph (lower). Right: smoothing and alignment of the CT (upper) and 3D photograph (lower).

Figure 2:

Particle representation and skin regression model. The proposed method first uses Shapeworks to automatically place corresponding points on skull/skin shapes of controls (left upper). Next, the corresponding points are generated for each shape with expert ratings (left lower). Principal component analysis is used to summarize the correspondences using low dimensional shape descriptors (right upper). Each Principal Component is characterized by the deviation of a blue mesh from the mean shape (wireframe) with 3 standard deviations. Finally, severity is assessed based on the predicted skull shape.

Figure 3:

Correlation between severity calculated from CT skull vs. CT skin (PCC r=0.92, SCC r=0.87, p<0.0001) (upper left); correlation between severity calculated from CT skull vs. 3D photograph (PCC r=0.82, SCC r=0.75) (upper right); correlation between severity calculated from CT skin vs. 3D photograph (PCC r=0.95, SCC r=0.92, p<0.0001) (lower left); Histogram showing the relative distribution of severities of metopic patients as calculated from 3D photographs compared to control patients evaluated by expert ratings and controls calculated from 3D photographs (lower right).

Figure 4:

Upper: 3D photograph (left) and CT image (right) of the patient with highest concordance. Lower: 3D photograph (left) and CT image (right) of the patient with lowest concordance.

Figure 5:

Upper: An example of hair shape and density interfering in 3D photograph analysis in an African American patient. Lower: An example of a crying patient, which resulted in artificially worsened trigonocephaly.

References

1. Ahammout C, Perez FA, Birgfeld CB, Koudstaal MJ, Ellenbogen RG, Lee A and Heike CL (2021). “Evaluating the Utility of Routine Computed Tomography Scans after Cranial Vault Reconstruction for Children with Craniosynostosis.” Plast Reconstr Surg 148(1): 63e–70e. -PubMed
1. Akan B and Veli İ (2020). “Evaluation of soft-tissue changes in young adults treated with the Forsus fatigue-resistant device.” Am J Orthod Dentofacial Orthop 157(4): 481–489.e482. -PubMed
1. Bhalodia R, Dvoracek LA, Ayyash AM, Kavan L, Whitaker R and Goldstein JA (2020). “Quantifying the Severity of Metopic Craniosynostosis: A Pilot Study Application of Machine Learning in Craniofacial Surgery.” Journal of Craniofacial Surgery 31(3): 697–701. -PMC -PubMed
1. Binning M, Ragel B, Brockmeyer DL, Walker ML and Kestle JR (2007). “Evaluation of the necessity of postoperative imaging after craniosynostosis surgery.” J Neurosurg 107(1 Suppl): 43–45. -PubMed
1. Brenner D, Elliston C, Hall E and Berdon W (2001). “Estimated risks of radiation-induced fatal cancer from pediatric CT.” AJR Am J Roentgenol 176(2): 289–296. -PubMed

3D Photography to Quantify the Severity of Metopic Craniosynostosis - PubMed (original) (raw)