Yanchen Guo1, Zongpai Zhang1, Shichun Chen1, Lijun Yin1, David C. Alsop2, and Weiying Dai1
1Department of Computer Science, State University of New York at Binghamton, Binghamton, NY, United States, 2Department of Radiology, Beth Israel Deaconess Medical Center & Harvard Medical School, Boston, MA, United States
1Department of Computer Science, State University of New York at Binghamton, Binghamton, NY, United States, 2Department of Radiology, Beth Israel Deaconess Medical Center & Harvard Medical School, Boston, MA, United States
The deep neural network (DNN) model, with the noise
structure learned and incorporated, demonstrates consistent improved
performance in removing the structured noise from the ASL functional images
compared to the DNN model without the explicitly incorporated noise structure.
Fig. 1. (a) network architecture of the DNN1. (b) network architecture of the DNN2. Each CNN layer contains convolution (Conv), Rectified Linear Units (ReLU), and batch normalization (BN). The size of each CNN layer is shown on the box. A kernel size of 3*3 is used for each convolution.
Fig. 3. An example of (a) ground-truth image, and (b) denoised image by the DNN1 model, (c) denoised image by the DNN2 model is shown.
