Skip to main content
main-content
Top

Hint

Swipe to navigate through the chapters of this book

2018 | OriginalPaper | Chapter

Complex Fully Convolutional Neural Networks for MR Image Reconstruction

Authors : Muneer Ahmad Dedmari, Sailesh Conjeti, Santiago Estrada, Phillip Ehses, Tony Stöcker, Martin Reuter

Published in: Machine Learning for Medical Image Reconstruction

Publisher: Springer International Publishing

share
SHARE

Abstract

Undersampling the k-space data is widely adopted for acceleration of Magnetic Resonance Imaging (MRI). Current deep learning based approaches for supervised learning of MRI image reconstruction employ real-valued operations and representations by treating complex valued k-space/spatial-space as real values. In this paper, we propose complex dense fully convolutional neural network (\(\mathbb {C}\)DFNet) for learning to de-alias the reconstruction artifacts within undersampled MRI images. We fashioned a densely-connected fully convolutional block tailored for complex-valued inputs by introducing dedicated layers such as complex convolution, batch normalization, non-linearities etc. \(\mathbb {C}\)DFNet leverages the inherently complex-valued nature of input k-space and learns richer representations. We demonstrate improved perceptual quality and recovery of anatomical structures through \(\mathbb {C}\)DFNet in contrast to its real-valued counterparts.
Literature
2.
go back to reference Huang, G., Liu, Z., Weinberger, K.Q.: Densely connected convolutional networks. CoRR abs/1608.06993 (2016) Huang, G., Liu, Z., Weinberger, K.Q.: Densely connected convolutional networks. CoRR abs/1608.06993 (2016)
3.
go back to reference Hyun, C.M., Kim, H.P., Lee, S.M., Lee, S., Seo, J.K.: Deep learning for undersampled MRI reconstruction. Phys. Med. Biol. (2018) Hyun, C.M., Kim, H.P., Lee, S.M., Lee, S., Seo, J.K.: Deep learning for undersampled MRI reconstruction. Phys. Med. Biol. (2018)
4.
go back to reference Hammernik, K., et al.: Learning a variational network for reconstruction of accelerated MRI data. Magn. Resonance Med. 79(6), 3055–3071 (2018) CrossRef Hammernik, K., et al.: Learning a variational network for reconstruction of accelerated MRI data. Magn. Resonance Med. 79(6), 3055–3071 (2018) CrossRef
5.
go back to reference Kinam, K., Dongchan, K., HyunWook, P.: A parallel MR imaging method using multilayer perceptron. Med. Phys. 44(12), 6209–6224 (2017) CrossRef Kinam, K., Dongchan, K., HyunWook, P.: A parallel MR imaging method using multilayer perceptron. Med. Phys. 44(12), 6209–6224 (2017) CrossRef
6.
go back to reference Lee, D., Yoo, J.J., Tak, S., Ye, J.C.: Deep residual learning for accelerated MRI using magnitude and phase networks. CoRR abs/1804.00432 (2018) Lee, D., Yoo, J.J., Tak, S., Ye, J.C.: Deep residual learning for accelerated MRI using magnitude and phase networks. CoRR abs/1804.00432 (2018)
7.
go back to reference Nyquist, H.: Certain topics in telegraph transmission theory. Trans. Am. Inst. Electr. Eng. 47(2), 617–644 (1928) CrossRef Nyquist, H.: Certain topics in telegraph transmission theory. Trans. Am. Inst. Electr. Eng. 47(2), 617–644 (1928) CrossRef
8.
go back to reference Ravishankar, S., Bresler, Y.: MR image reconstruction from highly undersampled k-space data by dictionary learning. IEEE Trans. Med. Imaging 30(5), 1028–1041 (2011) CrossRef Ravishankar, S., Bresler, Y.: MR image reconstruction from highly undersampled k-space data by dictionary learning. IEEE Trans. Med. Imaging 30(5), 1028–1041 (2011) CrossRef
9.
go back to reference Sawyer, A.M., et al.: Creation of fully sampled MR data repository for compressed sensing of the knee. Ge Healthcare (2013) Sawyer, A.M., et al.: Creation of fully sampled MR data repository for compressed sensing of the knee. Ge Healthcare (2013)
10.
go back to reference Schlemper, J., Caballero, J., Hajnal, J.V., Price, A.N., Rueckert, D.: A deep cascade of convolutional neural networks for MR image reconstruction. CoRR abs/1703.00555 (2017) Schlemper, J., Caballero, J., Hajnal, J.V., Price, A.N., Rueckert, D.: A deep cascade of convolutional neural networks for MR image reconstruction. CoRR abs/1703.00555 (2017)
11.
go back to reference Trabelsi, C., et al.: Deep complex networks. CoRR abs/1705.09792 (2017) Trabelsi, C., et al.: Deep complex networks. CoRR abs/1705.09792 (2017)
12.
go back to reference Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004) CrossRef Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004) CrossRef
13.
go back to reference Yoseob, H., Jaejun, Y., Hee, K.H., Jung, S.H., Kyunghyun, S., Chul, Y.J.: Deep learning with domain adaptation for accelerated projection reconstruction MR. Magn. Resonance Med. 80(3), 1189–1205 (2018) CrossRef Yoseob, H., Jaejun, Y., Hee, K.H., Jung, S.H., Kyunghyun, S., Chul, Y.J.: Deep learning with domain adaptation for accelerated projection reconstruction MR. Magn. Resonance Med. 80(3), 1189–1205 (2018) CrossRef
14.
go back to reference Zhu, B., Liu, J.Z., Cauley, S.F., Rosen, B.R., Rosen, M.S.: Image reconstruction by domain-transform manifold learning. Nature 555, 487 EP (2018) CrossRef Zhu, B., Liu, J.Z., Cauley, S.F., Rosen, B.R., Rosen, M.S.: Image reconstruction by domain-transform manifold learning. Nature 555, 487 EP (2018) CrossRef
Metadata
Title
Complex Fully Convolutional Neural Networks for MR Image Reconstruction
Authors
Muneer Ahmad Dedmari
Sailesh Conjeti
Santiago Estrada
Phillip Ehses
Tony Stöcker
Martin Reuter
Copyright Year
2018
DOI
https://doi.org/10.1007/978-3-030-00129-2_4

Premium Partner