Mariama Salifu1, Melissa Haskell2, and Douglas C Noll1
1Biomedical Engineering, University of Michigan, Ann Arbor, MI, United States, 2Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, United States
1Biomedical Engineering, University of Michigan, Ann Arbor, MI, United States, 2Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, United States
we
proposed using a 1D convolutional neural network(1D CNN) for oscillating steady state imaging (OSSI) signal combination of fMRI data to solve the frequency sensitivity issues associated with L2-norm
combined OSSI signals by directly estimating the BOLD signal from the OSSI signal.
Fig. 5. Human Subject: A-B, Activation maps computed from Pearson correlation coefficient with a threshold of 0.45. C-D, Compare time courses for two activation pixels in the visual cortex
Fig. 2. 1DCNN architecture, The input of the network is a 15s long 1D OSSI signal and its output is the corresponding 1D BOLD signal. 95% of the simulated BOLD and OSSI time courses were used for training while the remaining 5% were set aside for testing. L1 loss, ADAM optimizer with a learning rate of 0.007 was used for training the network.
