Clinical trial · Observational
Combing a Deep Learning-Based Radiomics With Liquid Biopsy for Preoperative and Non-invasive Diagnosis of Glioma
Combing a Deep Learning-Based MRI Multimodal Radiomics Method With Liquid Biopsy Technique for Preoperative and Non-invasive Diagnosis of Glioma Grading and Molecular Subtype
- Source
- ClinicalTrials.gov
- Retrieved
- Sep 8, 2026
- Layer
- normalized (units and labels harmonized; values unchanged)
- Run
- ING-CLINICALTRIALS-20260908-000001
Summary
Brief summary (as posted)
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
Conditions (3)
Free-text conditions as registered, with the CancerIndex entity they were reconciled to and the match type.
| Condition (as posted) | Mapped entity | Match | Confidence |
|---|---|---|---|
| Deep Learning | — | UNRESOLVED | — |
| Glioma (Diagnosis) | Glioma | ONTOLOGY_EXACT | 0.85 |
| Liquid Biopsy | — | UNRESOLVED | — |
Interventions
Interventions (1)
| Intervention | Type | Mapped drug | Match |
|---|---|---|---|
| Prediction of glioma grading and molecular subtype | Diagnostic Test | — | UNRESOLVED |
Design
Arms and outcomes
Arms (1)
- label
- glioma patients
- description
- 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.
- interventionNames
- Diagnostic Test: Prediction of glioma grading and molecular subtype
Primary outcomes (2)
- measure
- AUC value of prediction performance
- timeFrame
- 1 year
- description
- AUC=(Sensitivity+Specificity)-1
- measure
- Dice coefficient for evaluating semgmentation performance
- timeFrame
- 1 year
- description
- Dice=2TP/(2TP+FP+FN)
Eligibility
Eligibility (as posted)
- Sex
- All
- Minimum age
- 18 Years
Show eligibility criteria text
Inclusion Criteria: * 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 Exclusion Criteria: * 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
References
Publications (1)
- DERIVEDHu 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