CranioRate: An imaging-based, deep-phenotyping analysis toolset, repository, and online clinician interface for craniosynostosis

CranioRate：基于成像的深度表型分析工具集、存储库和在线临床医生界面，用于颅缝早闭

• 批准号: 10568654
• 负责人: Jesse Aaron Goldstein
• 金额: $ 71.67万
• 依托单位: UNIVERSITY OF UTAH
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-01 至 2028-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10568654
• 关键词: 3-Dimensional; Address; Adopted; Adverse effects; Affect; Age; Algorithms; Applications Grants; Area; Blindness; Cephalic; Childhood; Clinical; Clinical Data; Collaborations; Collection; Compensation; Complex; Counseling; Craniosynostosis; Data; Data Set; Databases; Decision Making; Development; Diagnosis; Disease; Dysmorphology; Ensure; Evaluation; FaceBase; Family; Future; Goals; Grant; Growth; Head; Human; Image; Impairment; Infant; Intervention; Intracranial Hypertension; Investigation; Joint structure of suture of skull; Lead; Left; Machine Learning; Measures; Morphology; Neurocognition; Neurocognitive; Neurocognitive Deficit; Operative Surgical Procedures; Outcome; Pathology; Patient Care; Patient imaging; Patients; Pattern; Phenotype; Photography; Physicians; Pilot Projects; Population; Postoperative Period; Process; Recommendation; Reconstructive Surgical Procedures; Reporting; Research; Research Design; Research Personnel; Research Project Grants; Risk; Scanning; Security; Severities; Shapes; Socialization; Statistical Models; Surface; Surgeon; System; Systems Analysis; Techniques; Technology; Three-dimensional analysis; United States; Variant; Vision; Visual; Work; X-Ray Computed Tomography; clinical center; clinically relevant; cloud based; cranium; data integrity; design; human imaging; imaging modality; improved; individual patient; infancy; insight; machine learning algorithm; machine learning method; machine learning model; novel; patient population; point of care; premature; prevent; prospective; prototype; repository; risk stratification; self esteem; shape analysis; standard of care; suture fusion; tool; web portal

PROJECT SUMMARY Title: CranioRate™: An image-based, deep-phenotyping analysis toolset, repository, and online clinician interface for craniosynostosis. The purpose of this research grant application is to build on the advanced machine learning (ML) tool developed as part of a pilot study (R21EB026061) that objectively quantifies cranial dysmorphology, or deep phenotypes, in patients with metopic craniosynostosis (MC). Abnormal cranial suture fusion (craniosynostosis) occurs in one of every 2500 infants born in the US, resulting in disrupted regional skull growth and an increased risk of elevated intracranial pressure, neurocognitive impairment and visual disturbances including blindness. Impaired skull growth along the fused suture and subsequent growth compensation in other areas of the skull lead to predictable head shape patterns in patients with craniosynostosis; surgery is recommended early in childhood to restore normal head shape and prevent neurocognitive sequelae. In our work to date, our team has developed an ML/statistical shape analysis system utilizing computed tomography (CT) scans of patients with MC. We have demonstrated that our deep ML algorithm is as effective as expert clinician ratings in assessing severity and more effective than standard craniometric tools. We have expanded our processes to include the analysis of 3D photography to increase accessibility and study post-operative head shape. Thus far, we have demonstrated equivalent severity ratings between 3D photographs and CT scans when obtained on the same patients. Finally, we have designed and implemented an online head shape portal (CranioRate™) that automates preprocessing and analysis such that users can upload their own patient images, where the resulting data contributes to clinical patient care as well as research endeavors. To date, over 30 clinicians have contributed almost 400 MC CT scans to our portal, making our metopic craniosynostosis imaging collection the largest reported. In the proposed work, we will refine our processing pipeline and shape analysis technologies, while expanding our capabilities to encompass all forms of craniosynostosis and a wider array of imaging modalities, and improve the functionality and security of the CranioRate™ portal. To pursue these aims, we will bring together a robust consortium of collaborators to contribute imaging and clinical data, empanel a scientific advisory board to ensure data integrity, and establish an open access human craniosynostosis image bank to allow further collaborations through FaceBase. Specific goals for the current project are to: 1) Further develop a set of robust, general morphological quantification technologies and cloud-based implementations that result in effective scientific and clinical tools; 2) Establish a shared-access, well-curated dataset that will leverage our multicenter collaborative network and partnership with FaceBase; 3) Identify and collect pertinent clinical data to extend the utility of our shape analysis tool and shared-access database. The results of this study will significantly improve the understanding of the phenotypic variation in patients with craniosynostosis and will pave the way for more substantial imaging-based research in this understudied population.

项目摘要 标题：CranioRate™：基于图像的深度表型分析工具集、存储库和在线 颅缝早闭的临床医生界面。 这项研究资助申请的目的是建立在先进的机器学习（ML）工具上 作为初步研究（R21 EB 026061）的一部分开发，该研究客观量化了颅骨畸形，或 深表型，在患者的额位颅缝早闭（MC）。异常颅缝融合 在美国出生的婴儿中，每2500名中就有1名发生颅缝早闭（craniosynostosis），导致区域性发育中断 颅骨生长和颅内压升高的风险增加，神经认知障碍， 视觉障碍，包括失明。颅骨沿融合缝沿着生长受损， 颅骨其他区域的生长补偿导致可预测的头部形状模式， 颅缝早闭;建议在儿童早期进行手术，以恢复正常的头部形状， 预防神经认知后遗症。 在我们迄今为止的工作中，我们的团队已经开发了一个ML/统计形状分析系统， MC患者的断层扫描（CT）。我们已经证明了我们的深度ML算法是 在评估严重程度方面，作为专家临床医师评级有效，并且比标准颅骨测量更有效 工具.我们已经扩展了我们的流程，包括3D摄影的分析，以增加 可及性和研究术后头部形状。到目前为止，我们已经证明了 在同一患者上获得的3D照片和CT扫描之间的评分。我们终于有 设计并实施了一个在线头部形状门户网站（CranioRate™）， 和分析，以便用户可以上传他们自己的患者图像， 临床病人护理以及研究工作。迄今为止，已有30多名临床医生 近400个MC CT扫描到我们的门户网站，使我们的颅缝早闭影像收集， 最大的报道。 在拟议的工作中，我们将完善我们的加工管道和形状分析技术， 扩大我们的能力，包括所有形式的颅缝早闭和更广泛的成像 模式，并提高CranioRate™门户网站的功能和安全性。为了实现这些目标， 我们将汇集一个强大的合作者联盟，贡献成像和临床数据， 设立一个科学顾问委员会，以确保数据的完整性，并建立一个开放获取的人类 颅缝早闭图像库，以允许通过FaceBase进一步合作。具体目标 目前的项目是：1）进一步开发一套强大的，一般形态量化 技术和基于云的实施，从而产生有效的科学和临床工具; 2） 建立一个共享访问、精心策划的数据集，该数据集将利用我们的多中心协作网络 并与FaceBase合作; 3）识别和收集相关的临床数据，以扩展我们的 形状分析工具和共享访问数据库。这项研究的结果将大大改善 了解颅缝早闭患者的表型变异，并为 在这一未充分研究的人群中进行更实质性的基于成像的研究。