radiomic feature extraction toolboxes matlab 2015b  (MathWorks Inc)

Journal: Proceedings of SPIE--the International Society for Optical Engineering

Article Title: Evaluating clinical and radiomic features for predicting lung cancer recurrence pre- and post-tumor resection

doi: 10.1117/12.3006091

Figure Lengend Snippet: Radiomic features analyzed in this study.

Article Snippet: Feature Extraction Tumor masks were imported into our in-house radiomic feature extraction toolboxes created in MATLAB ® 2015b (The Mathworks Inc., Natick, Massachusetts) and C++ ( https://isocpp.org ).

Techniques:

Journal: JNCI Cancer Spectrum

Article Title: Hypoxia-Related Radiomics and Immunotherapy Response: A Multicohort Study of Non-Small Cell Lung Cancer

doi: 10.1093/jncics/pkab048

Figure Lengend Snippet: The radiomics pipeline. After pretreatment (ie, baseline), imaging, and patient data are obtained, radiomic features are extracted from standard-of-care imaging studies ( yellow ). Radiologists mark target the lesions, and lesions are automatically (or semi-automatically) segmented. Radiomic features are then extracted from the region of interest ( purple ). Unstable, nonreproducible and correlated radiomic features are removed. The remaining features are combined with the pretreatment clinical covariates ( green ), and model building approaches are applied, which can be used for patient stratification and/or treatment selection.

Article Snippet: The tumor masks were imported into in-house radiomic feature extraction toolboxes created in MATLAB 2015b (The Mathworks Inc, Natick, MA) and C++ ( https://isocpp.org ).

Techniques: Imaging, Clinical Proteomics, Selection

Journal: JNCI Cancer Spectrum

Article Title: Hypoxia-Related Radiomics and Immunotherapy Response: A Multicohort Study of Non-Small Cell Lung Cancer

doi: 10.1093/jncics/pkab048

Figure Lengend Snippet: The heat map of concordance correlation coefficients, the correlation matrix for the “avatar” feature, and the Classification and Regression Tree (CART). A) The heat map plots the concordance correlation coefficients (CCC) of the radiomic features acquired by different segmentations and image acquisitions. Each column in the heat map represents a radiomic feature from the indicated feature group and region of interest (eg, intratumoral or peritumoral). The features are compared between different segmentation algorithms (ALG), different initial parameters (IP), and test-retest scans (RIDER). The green boxes represent higher (CCC > 0.95), blue boxes represent moderate (CCC ≥ 0.75 and CCC ≤ 0.95), and red boxes represent lower (CCC < 0.75) CCCs. B) The correlation matrix plots the radiomic features that were statistically significantly associated with overall survival in the univariable analysis. The most informative radiomic feature (gray-level co-occurrence matrix [GLCM] inverse difference) was correlated with 7 other features. C) CART analysis was used to identify patient risk groups based on a decision tree containing 1 radiomic feature and 2 clinical features. Patients were grouped from low-risk to very high-risk based on overall survival outcomes.

Article Snippet: The tumor masks were imported into in-house radiomic feature extraction toolboxes created in MATLAB 2015b (The Mathworks Inc, Natick, MA) and C++ ( https://isocpp.org ).

Techniques:

Journal: JNCI Cancer Spectrum

Article Title: Hypoxia-Related Radiomics and Immunotherapy Response: A Multicohort Study of Non-Small Cell Lung Cancer

doi: 10.1093/jncics/pkab048

Figure Lengend Snippet: Gray level co-occurrence matrix (GLCM) inverse difference radiomic feature and CAIX expression. A-D) The association between GLCM inverse difference and CAIX expression based off 2 different probesets: merck2-DQ892208_at is presented in panels A and B , and merck-NM_001216_at is presented in panels C and D . E) The association between the automated pathology IHC scoring for CAIX and GLCM inverse difference. F) The correlation between the automated pathology IHC scoring for CAIX and GLCM inverse difference. In panels A, C, and E , the Mann-Whitney U test was used to calculate 2-sided P values, and the error bars depict Tukey whiskers (fences). In panels B, D, and F , Pearson correlation coefficient was used to calculate 2-sided P values.

Article Snippet: The tumor masks were imported into in-house radiomic feature extraction toolboxes created in MATLAB 2015b (The Mathworks Inc, Natick, MA) and C++ ( https://isocpp.org ).

Techniques: Expressing, MANN-WHITNEY

Journal: bioRxiv

Article Title: Hypoxia-related radiomics predict immunotherapy response: A multi-cohort study of NSCLC

doi: 10.1101/2020.04.02.020859

Figure Lengend Snippet: Pre-treatment (baseline) patient data are obtained, including: clinical covariates and computational image-based features (Radiomics). Radiomic features are extracted from standard-of-care imaging studies (yellow). Radiologists mark target lesions and lesions are automatically (or semi-automatically) segmented. Radiomic features are extracted from region-of-interest (purple). Unstable, non-reproducible and correlated radiomic features are removed. The remaining features are combined with the pre-treatment clinical covariates (green) and predictive model building approaches are applied which can be used for patient stratification and/or treatment selection.

Article Snippet: The tumor mask images (i.e., tumor delineations) were imported into in-house radiomic feature extraction toolbox that was created using MATLAB ® 2015b (The Mathworks Inc., Natick, Massachusetts) and C++ ( https://isocpp.org ).

Techniques: Imaging, Clinical Proteomics, Selection

Journal: bioRxiv

Article Title: Hypoxia-related radiomics predict immunotherapy response: A multi-cohort study of NSCLC

doi: 10.1101/2020.04.02.020859

Figure Lengend Snippet: Each column in the heat map represents a radiomic feature from the indicated feature group and region-of-interest (e.g., intratumoral or peritumoral). The features are compared between different segmentation algorithms (ALG), different initial parameters (IP) and test-retest scans (RIDER). The green boxes represent higher (CCC > 0.95), blue boxes represent moderate (CCC ≥ 0.75 & CCC ≤ 0.95) and red boxes represent lower (CCC < 0.75) CCCs.

Article Snippet: The tumor mask images (i.e., tumor delineations) were imported into in-house radiomic feature extraction toolbox that was created using MATLAB ® 2015b (The Mathworks Inc., Natick, Massachusetts) and C++ ( https://isocpp.org ).

Techniques:

Journal: bioRxiv

Article Title: Hypoxia-related radiomics predict immunotherapy response: A multi-cohort study of NSCLC

doi: 10.1101/2020.04.02.020859

Figure Lengend Snippet: The Classification and Regression Tree (CART) was used to identify patient risk groups based on a model containing one radiomic feature and two clinical features. Patients were grouped from low risk to very high risk based on the CART decision nodes and terminal nodes.

Article Snippet: The tumor mask images (i.e., tumor delineations) were imported into in-house radiomic feature extraction toolbox that was created using MATLAB ® 2015b (The Mathworks Inc., Natick, Massachusetts) and C++ ( https://isocpp.org ).

Techniques:

Journal: bioRxiv

Article Title: Hypoxia-related radiomics predict immunotherapy response: A multi-cohort study of NSCLC

doi: 10.1101/2020.04.02.020859

Figure Lengend Snippet: Kaplan-Meier survival curves estimates for overall survival between identified risk groups in the A) training (MCC 1) cohort, B) Test (MCC 2) cohorts and C) Validation (VA) cohort, and progressive-free survival in D) Training (MCC 1) cohort and E) Test (MCC 2) cohort. Test for agreement between radiomic and pathological immune response assessment.

Article Snippet: The tumor mask images (i.e., tumor delineations) were imported into in-house radiomic feature extraction toolbox that was created using MATLAB ® 2015b (The Mathworks Inc., Natick, Massachusetts) and C++ ( https://isocpp.org ).

Techniques: Biomarker Discovery

Journal: bioRxiv

Article Title: Hypoxia-related radiomics predict immunotherapy response: A multi-cohort study of NSCLC

doi: 10.1101/2020.04.02.020859

Figure Lengend Snippet: Whisker-box plots representing the association between CAIX expression on immunohistochemical staining and GLCM inverse difference CT radiomic feature. High and low GLCM inverse difference was found using novel cut-point (0.43) defined by CART analysis.

Article Snippet: The tumor mask images (i.e., tumor delineations) were imported into in-house radiomic feature extraction toolbox that was created using MATLAB ® 2015b (The Mathworks Inc., Natick, Massachusetts) and C++ ( https://isocpp.org ).

Techniques: Whisker Assay, Expressing, Immunohistochemical staining, Staining

Journal: bioRxiv

Article Title: Hypoxia-related radiomics predict immunotherapy response: A multi-cohort study of NSCLC

doi: 10.1101/2020.04.02.020859

Figure Lengend Snippet: Representative cases for testing the agreement between GLCM inverse difference and CAIX IHC expression. Correlation between high CAIX and high CT radiomic feature is seen on left side and correlation between low CAIX and low CT radiomic feature is seen on right side.

Article Snippet: The tumor mask images (i.e., tumor delineations) were imported into in-house radiomic feature extraction toolbox that was created using MATLAB ® 2015b (The Mathworks Inc., Natick, Massachusetts) and C++ ( https://isocpp.org ).

Techniques: Expressing

Journal: Frontiers in Oncology

Article Title: Multiple Level CT Radiomics Features Preoperatively Predict Lymph Node Metastasis in Esophageal Cancer: A Multicentre Retrospective Study

doi: 10.3389/fonc.2019.01548

Figure Lengend Snippet: Workflow of the radiomics model building process. Image segmentation was performed by experienced radiology doctor on the CT image. The handcrafted features were extracted from the segmented image. For computer vision features and deep features, sub-images contain whole tumor were clipped from the segmented images, and then combined into a RGB image. Computer vision features and deep features were extracted from the RGB images. (A) Segmented images for extracting handcrafted features. (B,C) RGB images for computer vision and deep features extraction, respectively.

Article Snippet: A toolbox of radiomics feature extraction based on the Matlab 2016b was developed in-house.

Techniques: Extraction

Journal: Frontiers in Oncology

Article Title: Multiple Level CT Radiomics Features Preoperatively Predict Lymph Node Metastasis in Esophageal Cancer: A Multicentre Retrospective Study

doi: 10.3389/fonc.2019.01548

Figure Lengend Snippet: Risk factors for lymph node metastasis in patients with ESCC.

Article Snippet: A toolbox of radiomics feature extraction based on the Matlab 2016b was developed in-house.

Techniques:

Journal: Frontiers in Oncology

Article Title: Multiple Level CT Radiomics Features Preoperatively Predict Lymph Node Metastasis in Esophageal Cancer: A Multicentre Retrospective Study

doi: 10.3389/fonc.2019.01548

Figure Lengend Snippet: Radiomics nomogram of Model 3 for predicting the ESCC patients with LN metastasis (A) . Calibration curves of the radiomics nomogram in development cohort (B) , internal validation cohort (C) and external validation cohort (D) . Calibration curves reflect the calibration of Model 3 in terms of agreement between the predicted of LN metastasis and observed of LN metastasis. The 45-degree blue diagonal line represents a perfect ideal model. The closer the red dot-dash line is to the diagonal line, the better the prediction. (E–G) presents AUC values on the development, internal validation, and external validation cohort of Model 1, 2, and 3. Potential incremental value of models 2 and 3 relative to model 1 were evaluated by net reclassification improvement (NRI). (B,E) for development cohort, (C,F) for internal validation cohort, and (D,G) for external validation cohort.

Article Snippet: A toolbox of radiomics feature extraction based on the Matlab 2016b was developed in-house.

Techniques: Biomarker Discovery