Histopathology Images Based Survival Prediction of Glioma Patients Using Artificial Intelligence

Recruiting

• Conditions: Glioma

• Registration Number: NCT04215224
• Lead Sponsor: The First Affiliated Hospital of Zhengzhou University

Brief Summary

This registry aims to collect clinical, molecular and histopathology imaging including detailed survival data, clinical parameters, molecular pathology (1p/19q codeletion, 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 hstopathology imaging based algorithms that able to predict patients' survivals in the frame of molecular pathology or subgroups of gliomas.

Detailed Description

Non-invasive and precise prediction for survivals of glioma patients 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 patients' prognosis in the frame of molecular pathology of gliomas. The creation of a registry for primary glioma with detailed survival data, molecular pathology, histopathology image data and with sufficient sample size for deep learning (\>1000) provides opportunities for personalized prediction of survival of glioma patients with non-invasiveness and precision.

Study Timeline

• Study Start: 2017-01-01
• Study First Submitted: 2019-12-30
• Study First Submitted QC: 2019-12-30
• Study First Posted: 2020-01-02
• Status Verified: 2021-02
• Last Update Submitted: 2021-02-05
• Last Update Posted: 2021-02-08
• Primary Completion: 2027-01-01
• Study Completion: 2027-06-01

Recruitment & Eligibility

• Status: RECRUITING
• Sex: All
• Target Recruitment: 3500

Inclusion Criteria

• 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

Exclusion Criteria

• 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 malfuctions

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
AUC of survival prediction performance	up to 10 years	AUC of survival prediction performance=sensitivity+specificity-1

Trial Locations

Locations (1)

Department of Neurosurgery, First Affiliated Hospital of Zhengzhou University; 🇨🇳 Zhengzhou, Henan, China