Combing a Deep Learning-Based Radiomics With Liquid Biopsy for Preoperative and Non-invasive Diagnosis of Glioma

NCT05536024 | Unknown

• 1 other identifier: GliomaDL-1
• Study Type: observational
• Target: 500
• Locations: 1 country
• Sites: 2

Brief Summary

This registry has the following objectives. First, according to the guidance of 2021 WHO of CNS classification, we constructed and externally tested a multi-task DL model for simultaneous diagnosis of tumor segmentation, glioma classification and more extensive molecular subtype, including IDH mutation, ATRX deletion status, 1p19q co-deletion, TERT gene mutation status, etc. Second, based on the same ultimate purpose of liquid biopsy and radiomics, we innovatively put forward the concept and idea of combining radiomics and liquid biopsy technology to improve the diagnosis of glioma. And through our study, it will provide some clinical validation for this concept, hoping to supply some new ideas for subsequent research and supporting clinical decision-making.

Conditions

Glioma (Diagnosis); Liquid Biopsy; Deep Learning

Keywords

Glioma; Diagnostic model; radiomic; liquid biopsy

Outcome Measures

Primary Outcomes (2)

• AUC value of prediction performance

  AUC=(Sensitivity+Specificity)-1

  1 year

• Dice coefficient for evaluating semgmentation performance

  Dice=2TP/(2TP+FP+FN)

  1 year

Study Arms (1)

glioma patients

This study includes the glioma patients aged over 18 years, receiving surgical resection or needle biopsy for the first time, and without any radiotherapy and/or chemotherapy prior to preoperative MRI scan. All included glioma patients were redefined or newly diagnosed according to the 2021 WHO of CNS classification.

Diagnostic Test: Prediction of glioma grading and molecular subtype

Interventions

Prediction of glioma grading and molecular subtype DIAGNOSTIC_TEST

Prediction of WHO grading(II/III/IV), IDH gene mutation status, ATRX deletion status, 1p/19q deletion status, CDKN2A/B homozygous deletion status, TERT gene mutation status, epidermal growth factor receptor (EGFR) mutation status, chromosome 7gain and chromosome 10 less status, H3F3A G34 (H3.3 G34) mutation status, H3 K27M mutation status

glioma patients

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Patients with newly diagnosed glioma that receiving surgical resection or needle biopsy accoding to 2021 WHO of CNS classfication

You may qualify if:

• glioma patients with postoperative pathological examination
• age \>18 years old
• without any radiotherapy and/or chemotherapy prior to preoperative MRI scan
• receiving surgical resection or needle biopsy for the first diagnosis
• Signed informed consent

You may not qualify if:

• Non gliomas
• Without any preoperatiev MRI scan in Imaging Record System
• Or receiving radiotherapy and/or chemotherapy prior to preoperative MRI scan
• Rejecting surgical resection or needle biopsy

Sponsors & Collaborators

• Second Affiliated Hospital of Nanchang University: lead
• Renmin Hospital of Wuhan University: collaborator
• Wuhan University: collaborator

Study Sites (2)

Renmin Hospital of Wuhan University

Wuhan, Hubei, 430060, China

RECRUITING

The Second Affiliated Hospital of Nanchang University

Nanchang, Jiangxi, 330000, China

RECRUITING

Related Publications (1)

• Hu P, Xu L, Qi Y, Yan T, Ye L, Wen S, Yuan D, Zhu X, Deng S, Liu X, Xu P, You R, Wang D, Liang S, Wu Y, Xu Y, Sun Q, Du S, Yuan Y, Deng G, Cheng J, Zhang D, Chen Q, Zhu X. Combination of multi-modal MRI radiomics and liquid biopsy technique for preoperatively non-invasive diagnosis of glioma based on deep learning: protocol for a double-center, ambispective, diagnostical observational study. Front Mol Neurosci. 2023 May 2;16:1183032. doi: 10.3389/fnmol.2023.1183032. eCollection 2023.

  PMID: 37201155 DERIVED

MeSH Terms

Conditions

Glioma; Disease

Condition Hierarchy (Ancestors)

Neoplasms, Neuroepithelial; Neuroectodermal Tumors; Neoplasms, Germ Cell and Embryonal; Neoplasms by Histologic Type; Neoplasms; Neoplasms, Glandular and Epithelial; Neoplasms, Nerve Tissue; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Officials

• Xingen Zhu, Prof

  Second Affiliated Hospital of Nanchang University

  STUDY DIRECTOR

• Qianxue Chen

  Renmin Hospital of Wuhan University

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Xingen Zhu, Prof

CONTACT

138 0354 6020; zxg2008vip@163.com

Ping Hu, PhD;MD

CONTACT

13207109734; hp666edu@163.com

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Target Duration: 1 Year
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: September 8, 2022
• First Posted: September 10, 2022
• Study Start: May 1, 2022
• Primary Completion: May 1, 2023
• Study Completion: August 30, 2023
• Last Updated: September 10, 2022

Record last verified: 2022-09

Locations

CN (2)