Molecular Imaging Visualization of Tumor Heterogeneity in Non-small Cell Lung Cancer
Overview
- Phase
- Not Applicable
- Intervention
- Not specified
- Conditions
- NSCLC
- Sponsor
- The First Affiliated Hospital of Xiamen University
- Enrollment
- 150
- Locations
- 1
- Primary Endpoint
- Radiomic feature selection and model establishment
- Last Updated
- 5 years ago
Overview
Brief Summary
To assess the potential usefulness of radiogenomics for tumor driving genes heterogeneity in non-small cell lung cancer.
Detailed Description
Patients with advanced NSCLC underwent 18F-FDG PET/CT and PET/CT-guided synchronous targeted biopsy of primary and distant metastatic tumors. The LIFEx package was used to extract PET and CT radiomic features from primary and metastatic lesions. The radiomic ROI sites of primary and distant metastatic tumors were point-to-point corresponding to the PET/ CT-guided targeted biopsy sites. Whole exon sequencing of primary and distant metastatic tumor samples obtained by PET/CT-guided targeted biopsy was used to get genomic data of primary and distant metastatic tumor. Predictive radiogenomics models were established and validation.
Investigators
Eligibility Criteria
Inclusion Criteria
- •(i) adult patients (aged 18 years or order);
- •(ii) patients with suspected or newly diagnosed or previously treated malignant tumors (supporting evidence may include magnetic resonance imaging (MRI), CT, tumor markers and pathology report);
- •(iii) patients who had scheduled both 18F-FDG PET/CT scans and PET/CT guided biopsy;
- •(iv) patients who were able to provide informed consent (signed by participant, parent or legal representative) and assent according to the guidelines of the Clinical Research Ethics Committee.
Exclusion Criteria
- •(i) patients with non-malignant lesions;
- •(ii) patients with pregnancy;
- •(iii) the inability or unwillingness of the research participant, parent or legal representative to provide written informed consent.
Outcomes
Primary Outcomes
Radiomic feature selection and model establishment
Time Frame: 3 years
In this study, the investigators first selected the features with significant differences between genes mutant and wild type in the training set using the Mann-Whitney U test, obtaining a total of 53 features with p value \< 0.05. Then, the least absolute shrinkage and selection operator (LASSO) algorithm was used to select the optimal predictive features among the 53 selected in the training set. The LASSO algorithm adds a L1 regularization term to a least square algorithm to avoid overfitting. A prediction model was established by logistic regression, and the radiomics signature score (rad-score) for each participant was calculated based on the selected discriminating radiomic features. The model performance was tested in the validation set. The receiver operating characteristic (ROC) curve and the area under the curve (AUC) were used to evaluate the model performance in the training and validation sets.
Secondary Outcomes
- Radiomic feature extraction(30 days)
- Genes mutation detection(30 days)
- Image acquisition(30 days)