This is a matlab demo showing how to compute the diagnostic performance (differentiating between local recurrence vs. inflammation) of 42 cross-combinations derived from 6 feature selection methods and 7 classifiers.
Citation:
[1] Dongyang Du, Wenbing Lv et al. Machine learning methods for optimal differentiation of recurrence versus inflammation from post- therapy nasopharyngeal 18F-FDG PET/CT images. J Nucl Med, 2018 vol. 59 no. supplement 1 125
This matlab code contains a demo：
- “demo_tr_te_CI”: matlab codes to compute the diagnostic performance of cross-combinations by using differnet feature selection methods and machine-learning classifiers.
ACKNOWLEDGEMENTS: other software packages
- Giorgio Roffo (FSLib): https://www.mathworks.com/matlabcentral/fileexchange/56937-feature-selection-library
- Gavin Brown (FEAST): https://www.cs.man.ac.uk/~gbrown/fstoolbox/
- Chih-Chung Chang and Chih-Jen Lin (LIBSVM): https://www.csie.ntu.edu.tw/~cjlin/libsvm/