Zechen Zhou1, Yi Wang2, Johannes M. Peeters3, Peter Börnert4, Chun Yuan5, and Marcel Breeuwer3
1Philips Research North America, Cambridge, MA, United States, 2MR Clinical Science, Philips Healthcare North America, Gainesville, FL, United States, 3MR Clinical Science, Philips Healthcare, Best, Netherlands, 4Philips Research Hamburg, Hamburg, Germany, 5Vascular Imaging Lab, University of Washington, Seattle, WA, United States
1Philips Research North America, Cambridge, MA, United States, 2MR Clinical Science, Philips Healthcare North America, Gainesville, FL, United States, 3MR Clinical Science, Philips Healthcare, Best, Netherlands, 4Philips Research Hamburg, Hamburg, Germany, 5Vascular Imaging Lab, University of Washington, Seattle, WA, United States
Perceptual loss
function and multi-scale network structure can improve the generalization and
robustness of super resolution (SR) network performance. A single SR network
trained with brain data is feasible to perform well in knee and body imaging
applications.
Figure 4: Comparison
of super resolution (SR) results using different network architectures and
training datasets in abdominal imaging. HR: high resolution ground truth. L1
GAN: L1+advaserial loss. L1 GAN VGG: L1+adversarial+perceptual loss. Body/Brain
indicates the training datasets. The bottom two rows are the zoom-in views from
HR and different SR results in a same local region of the full field-of-view HR
body image. Note the SR performance difference for small image structures as
shown by the red arrows.
Figure 3: Comparison
of MSRES2NET based super resolution (SR) results using different loss functions
and training datasets in knee imaging. HR: high resolution ground truth. LR:
downsampled low resolution input. L1 GAN: L1+advaserial loss. L1 GAN VGG:
L1+adversarial+perceptual loss. Knee/Brain(mp)/Brain(all) indicates the
training datasets, where brain(mp) denotes to only use MPRAGE data and
brain(all) uses all of the brain data. Note the SR results difference for the ligament
regions (red circles) and small arteries (red arrows).