Soumick Chatterjee1,2,3, Chompunuch Sarasaen1,4, Alessandro Sciarra1,5, Mario Breitkopf1, Steffen Oeltze-Jafra5,6,7, Andreas Nürnberger2,3,7, and Oliver Speck1,6,7,8
1Department of Biomedical Magnetic Resonance, Otto von Guericke University, Magdeburg, Germany, 2Data and Knowledge Engineering Group, Otto von Guericke University, Magdeburg, Germany, 3Faculty of Computer Science, Otto von Guericke University, Magdeburg, Germany, 4Institute of Medical Engineering, Otto von Guericke University, Magdeburg, Germany, 5MedDigit, Department of Neurology, Medical Faculty, University Hopspital, Magdeburg, Germany, 6German Centre for Neurodegenerative Diseases, Magdeburg, Germany, 7Center for Behavioral Brain Sciences, Magdeburg, Germany, 8Leibniz Institute for Neurobiology, Magdeburg, Germany
1Department of Biomedical Magnetic Resonance, Otto von Guericke University, Magdeburg, Germany, 2Data and Knowledge Engineering Group, Otto von Guericke University, Magdeburg, Germany, 3Faculty of Computer Science, Otto von Guericke University, Magdeburg, Germany, 4Institute of Medical Engineering, Otto von Guericke University, Magdeburg, Germany, 5MedDigit, Department of Neurology, Medical Faculty, University Hopspital, Magdeburg, Germany, 6German Centre for Neurodegenerative Diseases, Magdeburg, Germany, 7Center for Behavioral Brain Sciences, Magdeburg, Germany, 8Leibniz Institute for Neurobiology, Magdeburg, Germany
The preliminary experiments with fastMRI dataset have
shown promising results. The network was able to reconstruct undersampled MRIs
with less to no artefact, and resulted in SSIM as high as 0.955, improving from
0.877.
Fig.2: Reconstruction result of the random variable density sampling, along with the fully-sampled image, undersampled (zero-padded) image and the corresponding difference images.
Fig.1. Network architecture and the workflow of the proposed complex valued residual neural network. The network is provided with undersampled k-space for each coil, treating each coil as different channel. The network also provided coil-wise k-space as output. The originally acquired data were then replaced in the output k-space as a data consistency step. 2D inverse fast Fourier transform (IFFT) was performed on this k-space to obtain the coil-wise reconstructed images. IFFT was also performed on the fully sampled k-space and then the loss was computed by comparing these images.
