CranioRate: An Image-Based, Deep-Phenotyping Analysis Toolset and Online Clinician Interface for Metopic Craniosynostosis

Abstract

Background: The diagnosis and management of metopic craniosynostosis involve subjective decision-making at the point of care. The purpose of this work was to describe a quantitative severity metric and point-of-care user interface to aid clinicians in the management of metopic craniosynostosis and to provide a platform for future research through deep phenotyping. Methods: Two machine-learning algorithms were developed that quantify the severity of craniosynostosis—a supervised model specific to metopic craniosynostosis [Metopic Severity Score (MSS)] and an unsupervised model used for cranial morphology in general [Cranial Morphology Deviation (CMD)]. Computed tomographic (CT) images from multiple institutions were compiled to establish the spectrum of severity, and a point-of-care tool was developed and validated. Results: Over the study period (2019 to 2021), 254 patients with metopic craniosynostosis and 92 control patients who underwent CT scanning between the ages of 6 and 18 months were included. CT scans were processed using an unsupervised machine-learning based dysmorphology quantification tool, CranioRate. The average MSS was 0.0 ± 1.0 for normal controls and 4.9 ± 2.3 (P < 0.001) for those with metopic synostosis. The average CMD was 85.2 ± 19.2 for normal controls and 189.9 ± 43.4 (P < 0.001) for those with metopic synostosis. A point-of-care user interface (craniorate.org) has processed 46 CT images from 10 institutions. Conclusions: The resulting quantification of severity using MSS and CMD has shown an improved capacity, relative to conventional measures, to automatically classify normal controls versus patients with metopic synostosis. The authors have mathematically described, in an objective and quantifiable manner, the distribution of phenotypes in metopic craniosynostosis.