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

Area of Science:

• Medical imaging analysis
• Computational biology
• Pediatric neurosurgery

Background:

• Metopic craniosynostosis diagnosis and management currently rely on subjective clinical judgment.
• Objective quantification is needed to improve diagnostic accuracy and treatment planning.
• Deep phenotyping platforms can enhance research into cranial development and disorders.

Purpose of the Study:

• To develop a quantitative severity metric for metopic craniosynostosis.
• To create a point-of-care user interface for clinical decision support.
• To establish a platform for advanced research in craniosynostosis through deep phenotyping.

Main Methods:

• Developed supervised (Metopic Severity Score - MSS) and unsupervised (Cranial Morphology Deviation - CMD) machine-learning algorithms.
• Compiled and analyzed computed tomographic (CT) images from multiple institutions.
• Created and validated a point-of-care tool (craniorate.org) for quantitative analysis.

Main Results:

• Included 254 patients with metopic craniosynostosis and 92 controls (ages 6-18 months).
• Demonstrated statistically significant differences in MSS and CMD between patients and controls (P < 0.001).
• The point-of-care interface has processed 46 CT images from 10 institutions.

Conclusions:

• Quantitative severity metrics (MSS and CMD) offer improved classification accuracy over conventional methods.
• Objective and quantifiable mathematical descriptions of metopic craniosynostosis phenotypes have been established.
• The developed tools provide a foundation for objective clinical management and further research.