From the Department of Plastic Surgery, University of Pittsburgh Medical Center.
University of Utah School of Computing.
Plast Reconstr Surg. 2024 Jan 1;153(1):112e-119e. doi: 10.1097/PRS.0000000000010452. Epub 2023 Mar 22.
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.
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.
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.
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.
额缝早闭的诊断和治疗涉及到在护理点进行主观决策。本研究的目的是描述一种定量严重程度指标和护理点用户界面，以帮助临床医生管理额缝早闭，并通过深度表型提供一个未来研究的平台。
开发了两种机器学习算法来量化颅缝早闭的严重程度——一种针对额缝早闭的有监督模型（额缝严重程度评分（MSS）），和一种用于一般颅形态的无监督模型（颅形态偏差（CMD））。从多个机构汇编了计算机断层扫描（CT）图像以建立严重程度谱，并开发和验证了一种护理点工具。
在研究期间（2019 年至 2021 年），纳入了 254 例额缝早闭患儿和 92 例 6 至 18 个月龄行 CT 扫描的对照组患儿。使用基于非监督机器学习的畸形量化工具 CranioRate 对 CT 扫描进行处理。正常对照组的平均 MSS 为 0.0±1.0，而额缝早闭组为 4.9±2.3（P<0.001）。正常对照组的平均 CMD 为 85.2±19.2，而额缝早闭组为 189.9±43.4（P<0.001）。一个护理点用户界面（craniorate.org）已经处理了来自 10 个机构的 46 个 CT 图像。
使用 MSS 和 CMD 进行的严重程度量化与传统测量方法相比，具有更好的自动分类正常对照组和额缝早闭组的能力。作者以客观和可量化的方式描述了额缝早闭的表型分布。
