Journal: Frontiers in Oncology

Article Title: Differentiating Peripherally-Located Small Cell Lung Cancer From Non-small Cell Lung Cancer Using a CT Radiomic Approach

doi: 10.3389/fonc.2020.00593

Figure Lengend Snippet: Schema for lung cancer segmentation, radiomic feature extraction and predictive modeling. (A) Representative CT images from small cell lung cancer (SCLC) and non-small cell lung cancer (NSCLC) showing tumor segmentation. (B) Illustrations of radiomic feature extraction for texture, shape, and intensity. (C) Decision of SCCL/NSCLC classification (upper panel) with the receiver operating characteristic (ROC) curves (middle panel) and the heat map of radiomic features (lower panel).

Article Snippet: We extracted the tumor textural features using the MATLAB radiomic package ( https://github.com/mvallieres/radiomics ) and the textural analysis formula ( ).

Techniques:

Journal: Frontiers in Oncology

Article Title: Differentiating Peripherally-Located Small Cell Lung Cancer From Non-small Cell Lung Cancer Using a CT Radiomic Approach

doi: 10.3389/fonc.2020.00593

Figure Lengend Snippet: The nnet architecture of the radiomics-based SCLC/NSCLC classifier. This figure presents the input layer with 20 nodes receiving 20 radiomic features, the 3 hidden layers for non-linear mapping, and the output layer with 2 nodes for “SCLC” and “NSCLC” decision upon a hard thresholding f(node)>0 and f(node)≤0, respectively. SCLC, small cell lung cancer; NSCLC, non-small cell lung cancer.

Article Snippet: We extracted the tumor textural features using the MATLAB radiomic package ( https://github.com/mvallieres/radiomics ) and the textural analysis formula ( ).

Techniques:

Journal: Frontiers in Oncology

Article Title: Differentiating Peripherally-Located Small Cell Lung Cancer From Non-small Cell Lung Cancer Using a CT Radiomic Approach

doi: 10.3389/fonc.2020.00593

Figure Lengend Snippet: The top 20 features selected from the radiomic data set (total 1,731 features) for the small cell lung cancer (SCLC) / non-small-cell lung cancer (NSCLC) classification. (A) Measurements for top 20 features. Each feature (matrix row) consisted of 35 SCLC measurements (index 1:35) and 34 NSCLC measurements (index 36:69). Each feature vector was normalized by max=1. (B) Mutual information map for the top 20 features. A large mutual information value indicated a high redundancy between the features.

Article Snippet: We extracted the tumor textural features using the MATLAB radiomic package ( https://github.com/mvallieres/radiomics ) and the textural analysis formula ( ).

Techniques: Plasmid Preparation

Journal: BMC Medical Research Methodology

Article Title: Externally validated and clinically useful machine learning algorithms to support patient-related decision-making in oncology: a scoping review

doi: 10.1186/s12874-025-02463-y

Figure Lengend Snippet: Characteristics, classification and objectives of the machine learning models used in the studies

Article Snippet: Varghese [ ] b , Incidence risk stratification (classification): QSVM (radiomics-based) , Risk stratification for prostate cancer in low- and high-risk patients , desktop-based , CDSS , MATLAB's Classification-Learner Package , NR , NR.

Techniques: Software, Biomarker Discovery, Diagnostic Assay, Imaging, Staining