<< Back to the abstract archive
Quantifying the Severity of Metopic Craniosynostosis
Erin Anstadt, MD; Madeleine Bruce, BA; Wenzheng Tao; Ejay Guo; Sneha Bhakare; Ladislav Kavan, PhD; Ross Whitaker, PhD; Jesse A Goldstein, MD
University of Pittsburgh Medical Center
2021-02-15
Presenter: Erin Anstadt
Affidavit:
Vu Nguyen
Director Name: Vu Nguyen
Author Category: Resident Plastic Surgery
Presentation Category: Clinical
Abstract Category: Craniomaxillofacial
Background: Quantifying the severity of head shape deformity and establishing a threshold for operative intervention remains challenging in patients with Metopic Craniosynostosis (MCS). This study combines 3D skull shape analysis with an unsupervised machine-learning algorithm to generate a quantitative shape severity score (MSS) and provide an operative threshold score.
Methods: Head computed tomography (CT) scans from subjects with MCS and normal controls (age 5-15 months) were used for objective 3D shape analysis using ShapeWorks software and in a survey for craniofacial surgeons to rate head-shape deformity and report whether they would offer surgical correction based on head shape alone. An unsupervised machine-learning algorithm was developed to quantify the degree of shape abnormality of MCS skulls compared to controls.
Results: 124 CTs were used to develop the model; 50 (24% MCS, 76% controls) were rated by 36 craniofacial surgeons, with an average of 20 ratings per skull. The interrater reliability was high (ICC=0.988). The algorithm performed accurately (AUC=0.97) and correlates closely with the surgeons assigned severity ratings (Spearman's Correlation coefficient r=0.779). The MSS ranges from 11-30; skulls with ratings ≥14 were highly likely to be offered surgery by the experts in this study.
Conclusions: This study provides an objective, quantitative severity score for MCS using a novel unsupervised machine-learning algorithm. The MSS provides a useful metric, especially in moderate phenotypes where clinical evaluation is less consistent. This is the first study to establish an operative threshold using 3D skull morphology in conjunction with expert rating data.
