Journal: Journal of Biomedical Optics
Article Title: Structured light imaging for breast-conserving surgery, part II: texture analysis and classification
doi: 10.1117/1.JBO.24.9.096003
Figure Lengend Snippet: Classification performance using subdiffuse reflectance ( f x = 1.37 mm − 1 , λ = 490 nm ) and evaluated by ROC curve analysis for (a) adipose, (b) connective, and (c) FCD, versus the three malignant tissue subtypes. Classification used a linear SVM classifier, correlation-based feature selection with grid-searching, fivefold CV, sample size matching, and averaging over n = 100 iterations. At most 11 texture features were included in each classification.
Article Snippet: Texture feature vectors (11 total features, detailed in ) associated with one benign tissue subtype and one malignant tissue subtype were classified using a linear SVM classifier (MATLAB function fitcsvm with default settings ) with correlation-based feature selection.
Techniques: Selection