Image processing and machine learning for telehealth craniosynostosis screening in newborns

View More View Less
  • 1 Division of Neurosurgery, Connecticut Children’s, Hartford;
  • 2 Department of Surgery, University of Connecticut Health Center, Farmington, Connecticut; and
  • 3 Department of Neurosurgery, Mayo Clinic, Rochester, Minnesota
Restricted access

Purchase Now

USD  $45.00

JNS + Pediatrics - 1 year subscription bundle (Individuals Only)

USD  $505.00

JNS + Pediatrics + Spine - 1 year subscription bundle (Individuals Only)

USD  $600.00
Print or Print + Online

OBJECTIVE

The authors sought to evaluate the accuracy of a novel telehealth-compatible diagnostic software system for identifying craniosynostosis within a newborn (< 1 year old) population. Agreement with gold standard craniometric diagnostics was also assessed.

METHODS

Cranial shape classification software accuracy was compared to that of blinded craniofacial specialists using a data set of open-source (n = 40) and retrospectively collected newborn orthogonal top-down cranial images, with or without additional facial views (n = 339), culled between April 1, 2008, and February 29, 2020. Based on image quality, midface visibility, and visibility of the cranial equator, 351 image sets were deemed acceptable. Accuracy, sensitivity, and specificity were calculated for the software versus specialist classification. Software agreement with optical craniometrics was assessed with intraclass correlation coefficients.

RESULTS

The cranial shape classification software had an accuracy of 93.3% (95% CI 86.8–98.8; p < 0.001), with a sensitivity of 92.0% and specificity of 94.3%. Intraclass correlation coefficients for measurements of the cephalic index and cranial vault asymmetry index compared to optical measurements were 0.95 (95% CI 0.84–0.98; p < 0.001) and 0.67 (95% CI 0.24–0.88; p = 0.003), respectively.

CONCLUSIONS

These results support the use of image processing–based neonatal cranial deformity classification software for remote screening of nonsyndromic craniosynostosis in a newborn population and as a substitute for optical scanner– or CT-based craniometrics. This work has implications that suggest the potential for the development of software for a mobile platform that would allow for screening by telemedicine or in a primary care setting.

ABBREVIATIONS AAA = anterior arc angle; AMWR = anterior-middle width ratio; CI = cephalic index; CVAI = cranial vault asymmetry index; PAA = posterior arc angle; ROC = receiver operating characteristic; TCLA = transcanthal line angle.

Supplementary Materials

    • eTables and eFigures (PDF 469 kb)

JNS + Pediatrics - 1 year subscription bundle (Individuals Only)

USD  $505.00

JNS + Pediatrics + Spine - 1 year subscription bundle (Individuals Only)

USD  $600.00

Contributor Notes

Correspondence Markus J. Bookland: Connecticut Children’s, Hartford, CT. mbookland@connecticutchildrens.org.

INCLUDE WHEN CITING Published online March 19, 2021; DOI: 10.3171/2020.9.PEDS20605.

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

  • 1

    Mawji A, Vollman AR, Hatfield J, . The incidence of positional plagiocephaly: a cohort study. Pediatrics. 2013;132(2):298304.

  • 2

    Fearon JA. Evidence-based medicine: craniosynostosis. Plast Reconstr Surg. 2014;133(5):12611275.

  • 3

    Proctor MR. Endoscopic craniosynostosis repair. Transl Pediatr. 2014;3(3):247258.

  • 4

    Seruya M, Oh AK, Boyajian MJ, . Age at initial consultation for craniosynostosis: comparison across different patient characteristics. J Craniofac Surg. 2013;24(1):9698.

    • Search Google Scholar
    • Export Citation
  • 5

    Rother C, Kolmogorov V, Blake A. Grabcut — interactive foreground extraction using iterative graph cuts. In: Marks J, ed. SIGGRAPH ’04: ACM SIGGRAPH 2004 Papers. ACM; 2004:309314.

    • Search Google Scholar
    • Export Citation
  • 6

    EMGU. Accessed November 13, 2020. http://www.emgu.com/wiki/index.php/Main_Page

  • 7

    Hu M-K. Visual pattern recognition by moment invariants. IRE Trans Inf Theory. 1962;8(2):179187.

  • 8

    Hinken L, Willenborg H, Dávila LA, Daentzer D. Outcome analysis of molding helmet therapy using a classification for differentiation between plagiocephaly, brachycephaly and combination of both. J Craniomaxillofac Surg. 2019;47(5):720725.

    • Search Google Scholar
    • Export Citation
  • 9

    Pickersgill NA, Skolnick GB, Naidoo SD, . Regression of cephalic index following endoscopic repair of sagittal synostosis. J Neurosurg Pediatr. 2018;23(1):5460.

    • Search Google Scholar
    • Export Citation
  • 10

    Bhalodia R, Dvoracek LA, Ayyash AM, . Quantifying the severity of metopic craniosynostosis: a pilot study application of machine learning in craniofacial surgery. J Craniofac Surg. 2020;31(3):697701.

    • Search Google Scholar
    • Export Citation
  • 11

    Porras AR, Tu L, Tsering D, . Quantification of head shape from three-dimensional photography for presurgical and postsurgical evaluation of craniosynostosis. Plast Reconstr Surg. 2019;144(6):1051e1060e.

    • Search Google Scholar
    • Export Citation
  • 12

    Pindrik J, Molenda J, Uribe-Cardenas R, . Normative ranges of anthropometric cranial indices and metopic suture closure during infancy. J Neurosurg Pediatr. 2016;25(6):667673.

    • Search Google Scholar
    • Export Citation
  • 13

    Slater BJ, Lenton KA, Kwan MD, . Cranial sutures: a brief review. Plast Reconstr Surg. 2008;121(4):170e178e.

Metrics

All Time Past Year Past 30 Days
Abstract Views 456 456 240
Full Text Views 38 38 22
PDF Downloads 17 17 13
EPUB Downloads 0 0 0