Jonathan Weine1, Robbert J. H. van Gorkum1, Christian T. Stoeck1, Valery Vishnevskiy1, Thomas Joyce1, and Sebastian Kozerke1
1Institute for Biomedical Engineering, University and ETH Zurich, Zürich, Switzerland
1Institute for Biomedical Engineering, University and ETH Zurich, Zürich, Switzerland
We present a feasibility study of training a residual
CNN on simulated data to infer diffusion tensors from unregistered free breathing
single-shot 2nd order
motion-compensated diffusion-weighted SE-EPI data. Improvement in resulting
parameter maps at myocardial borders is demonstrated.
Figure 1: Architecture design of the proposed residual CNN. Input is 144 stacked diffusion-weighted magnitude images, normalized to the mean LV intensity of the first image. The final output 6 channels represents the tensor entries. Convolutional layers (blue) have a $$$3\times3\times N$$$ kernel and ReLU activation. The residual blocks (green) consist of the parallel paths with different kernel sizes. The outputs are concatenated and reduced 1 convolution layer to match the input channels. The output of a residual block is added to the skip connection and fed to the next block.
Figure 2: Illustration of the
simulated training data and visual comparison to real in vivo data. (a)
Animation of single averages for each linear diffusion-weighting and (b)
example of the correspondingly simulated and LV-masked training dataset. The
red contours show a dilated LV-mask in which the inference on the unregistered
data is performed. (c-d) Maps of mean MD, FA as well as an artificial lesion map resulting serving as ground truth of
the simulated dataset.
