Histopathology Images Based Prediction of Molecular Pathology in Glioma Using Deep Learning or Machine Learning
试验速览
- 阶段
- 不适用
- 状态
- 招募中
- 发起方
- 入组人数
- 3,000
- 试验地点
- 1
- 主要终点
- AUC of prediction performance
研究概览
简要总结
This registry aims to collect clinical, molecular and radiologic data including detailed clinical parameters, molecular pathology (1p/19q co-deletion, MGMT methylation, IDH and TERTp mutations, etc) and images of HE slices in primary gliomas. By leveraging artificial intelligence, this registry will seek to construct and refine histopathology image based algorithms that are able to predict molecular pathology or subgroups of gliomas.
详细描述
Non-invasive and precise prediction for molecular biomarkers such as 1p/19q co-deletion, MGMT methylation, IDH and TERTp mutations is challenging. With the development of artificial intelligence, much more potential lies in the histopathology images of HE slices in primary gliomas could be excavated to aid prediction of molecular pathology of gliomas. The creation of a registry for primary glioma with detailed molecular pathology, histopathology image data and with sufficient sample size for deep learning (>1000) provide considerable opportunities for personalized prediction of molecular pathology with non-invasiveness and precision.
研究设计
- 研究类型
- Observational
- 观察模型
- Cohort
- 时间视角
- Other
入排标准
- 年龄范围
- 1 Year 至 95 Years（Child, Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 是
入选标准
- •Patients must have radiologically and histologically confirmed diagnosis of primary glioma
- •Life expectancy of greater than 3 months
- •Must receive tumor resection
- •Signed informed consent
排除标准
- •No gliomas
- •No sufficient amount of tumor tissues for detection of molecular pathology
- •Patients who are pregnant or breast feeding
- •Patients who are suffered from severe systematic malfunctions
结局指标
主要结局
AUC of prediction performance
时间窗: up to 10 years
AUC=sensitivity+specificity-1
次要结局
未报告次要终点
研究者
Zhenyu Zhang
Principal Investigator
The First Affiliated Hospital of Zhengzhou University