Jianpan Huang1, Joseph H. C. Lai1, Kai-Hei Tse2, Gerald W.Y. Cheng2, Xiongqi Han1, Yang Liu1, Zilin Chen1, Lin Chen3,4, Jiadi Xu3,4, and Kannie W. Y. Chan1,4,5
1Department of Biomedical Engineering, City University of Hong Kong, Hong Kong, China, 2Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, China, 3F.M. Kirby Research Center for Functional Brain Imaging, Kennedy Krieger Research Institute, Baltimore, MD, United States, 4Russell H. Morgan Department of Radiology and Radiological Science, The Johns Hopkins University School of Medicine, Baltimore, MD, United States, 5City University of Hong Kong Shenzhen Research Institute, Shenzhen, China
1Department of Biomedical Engineering, City University of Hong Kong, Hong Kong, China, 2Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, China, 3F.M. Kirby Research Center for Functional Brain Imaging, Kennedy Krieger Research Institute, Baltimore, MD, United States, 4Russell H. Morgan Department of Radiology and Radiological Science, The Johns Hopkins University School of Medicine, Baltimore, MD, United States, 5City University of Hong Kong Shenzhen Research Institute, Shenzhen, China
Deep neural network based CEST/AREX were exploited to analyze CEST data of mouse brains with Alzheimer’s disease (AD). Significant lower CEST/AREX signals related to amyloid β-peptide plaques were detected in AD mouse brains compared to age-matched WT mouse brains.
Figure 1. The schematics of CESTNet (A) and AREXNet (B).
Figure 3. Representative CEST and AREX maps of WT and AD brains, generated by trained CESTNet and AREXNet. CEST maps (AAPT, ArNOE and AMT) of central (A) and anterior slice (B). AREX maps (RAPT, RrNOE and RMT) of central slice (C) and anterior slice (D).
