Establishment and Evaluation of Multimodal Image Recognition System of Glioma Based on Deep Learning

Study Results

Results pending

The study team has not published outcome measurements, participant flow, or safety data for this trial yet. Check back later for updates.

Basic Information

Get a concise snapshot of the trial, including recruitment status, study phase, enrollment targets, and key timeline milestones.

Recruitment Status

UNKNOWN

Total Enrollment

350 participants

Study Classification

OBSERVATIONAL

Study Start Date

2021-12-30

Study Completion Date

2022-12-30

Brief Summary

Review the sponsor-provided synopsis that highlights what the study is about and why it is being conducted.

Research purposes:

1. To obtain the metabolic characteristics of glioma molecular imaging through a multimodal image recognition system.
2. To determine whether molecular imaging metabolic parameters can characterize the molecular typing of glioma by analyzing the relationship between metabolic parameters and tumor subtypes
3. To get metabolic classification based on metabolic parameters of glioma molecular imaging, and to identify the relationship between metabolic subtypes and surgical resection, radiotherapy and chemotherapy, and prognosis and further refine the molecular classification of glioma.

Research Background:

Glioma is the most common primary intracranial malignant tumor, accounting for 80% of central nervous system malignant tumors. It is highly invasive, with a surgical recurrence rate of up to 90%. The prognosis is extremely poor, which has caused a great burden. There are different molecular subtypes of glioma with distinct molecular biological characteristics, resulting in various prognosis of patients. With the continuous development of basic and clinical research of glioma and the advent of various new drugs and treatment technologies, molecular pathological diagnosis based on the individual level of glioma patients is particularly important. Clarifying the molecular pathology type before surgery will help the clinical diagnosis and prognostic judgment of glioma, and is of great significance for the optimization of treatment options.

Based on the establishment of glioma molecular typing system, the project team use noninvasive molecular imaging technology to clarify the characteristics of molecular subsets of glioma based on the tumor metabolic parameters. Through combining deep learning-based target detection and image recognition with big data analysis, it has great potential in the clinical research of glioma diagnosis, prognosis and treatment options, which could provide a scientific basis for the establishment and promotion of glioma molecular analysis and recognition system.

Related Clinical Trials

Explore similar clinical trials based on study characteristics and research focus.

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

NCT05536024

Glioma (Diagnosis) Liquid Biopsy Deep Learning

UNKNOWN

MR Based Prediction of Molecular Pathology in Glioma Using Artificial Intelligence

NCT04217018

Glioma

RECRUITING

Hierarchical Diagnosis for Adult Diffuse Glioma Based on Deep Learning

NCT05624736

Astrocytoma Glioblastoma Multiforme Oligodendroglioma

UNKNOWN

MR Based Survival Prediction of Glioma Patients Using Artificial Intelligence

NCT04215211

Glioma

RECRUITING

Multimodality Imaging Combined With Multiple Targets Pathological Examination for Detecting of Biological Borders of Gliomas: a Clinical Application Study

NCT02941302

Glioma

UNKNOWN NA

Detailed Description

Dive into the extended narrative that explains the scientific background, objectives, and procedures in greater depth.

1. Multimodal Image Recognition System of Glioma Molecular imaging is the use of imaging methods to display specific molecules at the tissue level, cellular level, and subcellular level, reflecting changes in the molecular level in the living state, and performing qualitative and quantitative researches on the biological behavior of the imaging aspect. Multimodal Image Recognition System includes Positron Emission Computed Tomography (PET), Magnetic Resonance Imaging (MRI) and Magnetic Resonance Hydrogen Proton Spectroscopy (1H-MRS). 1H-MRS quantifies the choline (Cho) and creatine (Cr) in the spectrum, N-acetylaspartate acid (NAA), qualification (Lip) and lactic acid (Lac) and other substances to reflect changes in cell metabolites, and then speculate on the occurrence and development of tumors. Imaging of the glucose analog 18F-labeled fluorodeoxyglucose (18FDG) by positron emission tomography (PET) is the gold standard for the assessment of cerebral glucose metabolism in vivo. However, single imaging method often has limitations, and it is difficult to meet the requirements for sensitivity, specificity, and target at the same time. Combing PET / CT with 1H- MRS of new generation imaging technologies can overcome the shortcomings of a single imaging method and achieve complementary advantages and provide effective informations
2. Risks and Benefits of Participants (1) Risks: In addition to collecting information above, the main risk is discomfort that may occur during the conversation. Since this study will not intervene in routine diagnosis and treatment, there are no other special risks other than the possible discomfort and adverse reactions mentioned above expected during treatment. (2) Benefits: No direct benefits, but may provide useful informations for disease research.
3. Statistical Methods All data (clinical data, imaging data) will be established in a special database. In order to control the imbalance of many different confounding factors in the formed population, the test will use the propensity score method to achieve the purpose of controlling confounding and improve the quality of real-world evidence, close to the effect of randomization.
4. Criteria for aborting trials and ending clinical trials

1\. Criteria for aborting trials The investigator judges that continuing the trial is not good for the patient; During the course of the study, the patient is unwilling to continue the clinical study, and makes a withdrawal request to the competent doctor and requests to cancel the informed consent.

2\. Criteria for ending clinical research: If serious safety problems occur during the study, the study should be terminated in time; The ethics committee requested to terminate the trial after the study; The health administrative department ordered the termination of clinical research for some reason; Significant deviations have occurred in the design or implementation of the study protocol and it is difficult to evaluate the results.

5\. Participant's Code, Storage Procedure of Case Report, Data Management and Guarantee of Test Reliability

1. After the participants enter the cohort after signing the informed consent, they will be sorted and assigned a serial number by the research secretary according to the time when the informed consent is signed. Therefore, the first patient enrolled is coded 001.
2. The patient's case report form will be made into a special patient manual, which will be kept by the research secretary and clinical staff for data collection and follow-up. Any observations and inspection results during the test should be entered into the form and database in a timely, accurate, complete, clear, standardized, and true manner. After the subject's follow-up is over, hand over and perform data collection and analysis. The subject's imaging data will be regularly uploaded by the research secretary to the intelligent IT virtual storage system based on the cluster. The system divides neurosurgery and subjects into specific storage partitions.
3. Each researcher has the authority to consult and modify the subject's storage partition. The storage system automatically records the changes of the stored data, thus ensuring the traceability of the data. The investigator should agree to keep all research data (including original records, informed consent of all patients, all case report forms, etc.), and the special counter shall be locked and stored until 5 years after the end of the trial.

6\. Safety

1. Serious adverse event: death; medical personnel believe what is life-threatening; events requiring hospitalization or extension of hospital stay; persistent or severe disability or disability.
2. Reporting methods and measures after the occurrence of the adverse events above, the medical staff should first report to the main investigator and fill out the adverse event report form. The adverse reaction report includes the diagnosis and treatment of the patient, the time of the event, the cause of the event and the treatment after the event. Provide timely diagnosis and treatment after serious adverse events, and report to the ethics committee within 24 hours. Report regularly according to the requirements of the ethics committee.

7\. Ethical requirements

1. Follow the Declaration of Helsinki.
2. Recruitment and informed process: The main investigator and his team members will recruit the subjects in the clinics or wards, inform the research content and related matters in detail, and read and sign the informed consent form before enrollment.
3. All trials will be conducted after obtaining the approval of the Ethics Committee of Qian Foshan Hospital in Shandong Province as well as follow-up review.

Conditions

See the medical conditions and disease areas that this research is targeting or investigating.

Glioma

Study Design

Understand how the trial is structured, including allocation methods, masking strategies, primary purpose, and other design elements.

Observational Model Type

COHORT

Study Time Perspective

PROSPECTIVE

Study Groups

Review each arm or cohort in the study, along with the interventions and objectives associated with them.

Glioma molecular subtype: G-CIMP-low

one of molecular subtypes according to gene expression, DNA copy number, DNA methylation, exome sequencing and protein expression of glioma