Fig. 3
From: A practical Alzheimer’s disease classifier via brain imaging-based deep learning on 85,721 samples
Performance of the Alzheimer’s disease (AD) classifier. Left panel shows the training and testing performance of the AD classifier on ADNI sample. Right panel shows the testing performance of the AD classifier on independent samples. (A) The receiver operating characteristic curve of the AD classifier. (B) The tensorboard monitor panel of the AD classifier in the training sample. (C) The tensorboard monitor panel of the AD classifier in the validation sample. (D) The ROC curve of AD classifier tested on the AIBL sample. (E) The ROC curve of the AD classifier tested on the MIRIAD sample. (F) The ROC curve of the AD classifier tested on the OASIS sample. (G) The ROC curve of the AD classifier tested on the ADNI MCI sample