Chemical exchange saturation transfer (CEST) magnetic resonance imaging (MRI) is a promising molecular imaging technology. Apparent exchange-dependent relaxation (AREX) provides CEST contrast with less influence of T1. Here, deep neural network based CEST/AREX analysis methods (CESTNet/AREXNet) were applied to analyze the CEST data of normal and AD mouse brains at 3T. Significant lower amide proton transfer/magnetization transfer (APT/MT) signals related to amyloid β-peptide (Aβ) plaque depositions, which were validated by immunohistochemistry results, were detected in Alzheimer’s disease (AD) mouse brains compared to age-matched wild type (WT) mouse brains. The well-established CESTNet/AREXNet have great potential to facilitate AD identification at 3T.