Journal: Health Information Science and Systems
Article Title: Automatic detection of gastrointestinal system abnormalities using deep learning-based segmentation and classification methods
doi: 10.1007/s13755-025-00354-6
Figure Lengend Snippet: Confusion matrices obtained by SVM classification of the best features selected by mRMR feature selection method (cross validation/k = 5): a the top 1000 features b the top 700 features c the top 500 features d the top 300 features, e the top 100 features
Article Snippet: The algorithm ranks each feature and evaluates their relationships, defining less important features as “redundant” and significant ones as “relevant.” This process was carried out using MATLAB’s Feature Selection Methods tool.
Techniques: Selection, Biomarker Discovery