Fig. 6From: Optimal transport- and kernel-based early detection of mild cognitive impairment patients based on magnetic resonance and positron emission tomography imagesAUC curves of BAg of our OT transfer learning framework. Panels A, B, and C correspond to results on the FDG, VBM, and combination of two data modalities respectively. The highest AUC curve is achieved by using SD combined with L1l2 regularization term as OT mapping cost function and linear kernel logistic regression as classifierBack to article page