<< Back to the abstract archive
CranioRate: An Image-Based, Deep-Phenotyping Analysis Toolset, Repository, and Online Clinician Interface for Craniosynostosis
Justin Beiriger, BSE; Madeleine Bruce, BA; Wenzheng Tao; Ross Whitaker, PhD; Jesse Goldstein, MD
UPMC
2022-01-05
Presenter: Justin Beiriger
Affidavit:
The majority of the work on this project represents the original work of the presenting medical student, Justin Beiriger.
Director Name: Vu Nguyen
Author Category: Medical Student
Presentation Category: Clinical
Abstract Category: Craniomaxillofacial
Introduction
The diagnosis and management of metopic craniosynostosis involves subjective decision-making by craniofacial and neurosurgeons at the point of care. The purpose of this work is 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 (Metopic Severity Score) and an unsupervised (Deep) model used for cranial morphology in general (Cranial Morphology Deviation). CT imaging from multiple institutions were compiled to establish the spectrum of severity and a point-of-care tool was developed and implemented.
Results
Over the study period (2019-2021), 244 patients with metopic craniosynostosis and 92 normal control patients who underwent CT scan between the ages of 3 and 18 months were included. Scans were processed using the CranioRateTM algorithm. The average MSS for normal controls was 0.0 ± 1.0 and for metopic synostosis was 5.0 ± 2.4 (p<0.001). The average CMD for normal controls was 85.2 ± 19.2 and for metopic synostosis was 193.7 ± 43.4 (p<0.001). Additionally, a point-of-care user interface (craniorate.org) has processed over 40 CT images from 10 institutions.
Conclusion
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. We have mathematically described, in an objective and quantifiable manner, the distribution of phenotypes in metopic craniosynostosis.
