A Hybrid Frequency-domain/Image-domain Deep Network for Magnetic Resonance Image Reconstruction

  • Roberto Souza University of Calgary
  • Richard Frayne University of Calgary

Resumo


Decreasing magnetic resonance (MR) image acquisition times can make MR examinations more accessible. Compressed sensing (CS)-based image reconstruction methods, decrease MR acquisition time by reconstructing high-quality images from data that were originally sampled at rates inferior to the Nyquist-Shannon sampling theorem. Iterative algorithms are the standard approach to solving ill-posed, CS inverse problems. These solutions are slow, thus, preventing near-real time image reconstruction. Recently, deep-learning methods have been used to solve the CS MR reconstruction problem. These proposed methods have the advantage of being able to quickly reconstruct images in a single pass using an appropriately trained network. A variety of different network architectures have been proposed to tackle the CS reconstruction problem. A drawback of these architectures is that they typically only work on image domain. In this work we propose a hybrid architecture that works both in k-space (frequency) and image domains. Our network is composed of a complex-valued residual U-net in the k-space domain, an iFFT operation, and a real-valued U-net in the image domain. Our experiments demonstrated, that the proposed hybrid approach can potentially improve CS reconstruction compared to deep-learning networks that operate only in the image domain. In this study we compare our method with four previously published deep neural networks and examine their ability to reconstruct images that are subsequently used to generate regional volume estimates. We evaluated undersampling ratios of 75% and 80%. Our technique was ranked second in the quantitative analysis, but qualitative analysis indicated that our reconstruction performed the best in hard to reconstruct regions, such as the cerebellum. Images reconstructed with our method were successfully post-processed, and showed good volumetry agreement compared with the fully sampled reconstruction measures.

Palavras-chave: compressed sensing, MR reconstruction

Referências

M. Lustig D. Donoho J. M. Pauly "Sparse MRI: The application of compressed sensing for rapid MR imaging" Magnetic Resonance in Medicine vol. 58 no. 6 pp. 1182-12007.

M. Lustig D. L. Donoho J. M. Santos J. M. Pauly "Compressed sensing MRI" IEEE Signal Processing Magazine vol. 25 no. 2 pp. 72-82 2008.

Y. LeCun Y. Bengio G. Hinton "Deep learning" Nature vol. no. 7pp. 2015.

G. Wang J. C. Ye K. Mueller J. A. Fessler "Image reconstruction is a new frontier of machine learning" IEEE Transactions on Medical Imaging vol. 37 no. 6 pp. 1289-12018.

G. Yang S. Yu H. Dong G. Slabaugh P. L. Dragotti X. Ye F. Liu S. Arridge J. Keegan Y. Guo "DAGAN: Deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction" IEEE Transactions on Medical Imaging vol. 37 no. 6 pp. 1310-12018.

K. H. Jin M. T. McCann E. Froustey M. Unser "Deep convolutional neural network for inverse problems in imaging" IEEE Transactions on Image Processing vol. 26 no. 9 pp. 4509-42017.

O. Ronneberger P. Fischer T. Brox "U-net: Convolutional networks for biomedical image segmentation" International Conference on Medical image computing and computer-assisted intervention pp. 234-2015.

T. M. Quan T. Nguyen-Due W.-K. Jeong "Compressed sensing MRI reconstruction using a generative adversarial network with a cyclic loss" IEEE Transactions on Medical Imaging vol. 37 no. 6 pp. 1488-12018.

J. Schlemper J. Caballero J. V. Hajnal A. N. Price D. Rueckert "A deep cascade of convolutional neural networks for dynamic MR image reconstruction" IEEE transactions on Medical Imaging vol. 37 no. 2 pp. 491-2018.

J.-Y. Y T. Park P. Isola A. A. Efros Unpaired image-to-image translation using cycle-consistent adversarial networks 2017.

B. Zhu J. Z. Liu S. F. Cauley B. R. Rosen M. S. Rosen "Image reconstruction by domain-transform manifold learning" Nature vol. no. 7pp. 2018.

T. Eo H. Shin T. Kim Y. Jun D. Hwang "Translation of 1d inverse fourier transform of k-space to an image based on deep learning for accelerating magnetic resonance imaging" International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) pp. 241-2018.

J. Schlemper I. Oksuz J. Clough J. Duan A. King J. Schanbel J. Hajnal D. Rueckert "dAUTOMAP: Decomposing AUTOMAP to achieve scalability and enhance performance" International Society for Magnetic Resonance in Medicine (ISMRM) 2019.

T. Eo Y. Jun T. Kim J. Jang H.-J. Lee D. Hwang "Kiki-net: cross-domain convolutional neural networks for reconstructing undersampled magnetic resonance images" Magnetic Resonance in Medicine vol. 80 no. 5 pp. 2188-22018.

J. Adler O. Oktem "Learned primal-dual reconstruction" IEEE Transactions on Medical Imaging vol. 37 no. 6 pp. 1322-12018.

R. Souza R. M. Lebel R. Frayne "A hybrid dual domain cascade of convolutional neural networks for magnetic resonance image reconstruction" Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning ser. Proceedings of Machine Learning Research vol. pp. 437-08–10 Jul 2019.

P. Zhang F. Wang W. Xu Y. Li "Multi-channel generative adversarial network for parallel magnetic resonance image reconstruction in k-space" International Conference on Medical Image Computing and Computer-Assisted Intervention pp. 180-188.

R. Souza O. Lucena J. Garrafa D. Gobbi M. Saluzzi S. Appenzeller L. Rittner R. Frayne R. Lotufo "An open multi-vendor multi-field-strength brain MR dataset and analysis of publicly available skull stripping methods agreement" N euroImage 2017.

F. Chollet et al. Keras 2015 [online] Available: https://github.com/fchollet/keras.

M. Abadi et al. TensorFlow: Large-scale machine learning on heterogeneous systems 2015.

A. Tsang C. A. Lebel S. L. Bray B. G. Goodyear M. Hafeez R. C. Sotero C. R. McCreary R. Frayne "White matter structural connectivity is not correlated to cortical resting-state functional connectivity over the healthy adult lifespan" Frontiers in Aging Neuroscience vol. 9 pp. 2017.

Z. Wang A. C. Bovik H. R. Sheikh E. P. Simoncelli "Image quality assessment: from error visibility to structural similarity" IEEE Transactions on Image Processing vol. 13 no. 4 pp. 600-2004.

B. Fischl "Freesurfer" NeuroImage vol. 62 no. 2 pp. 774-2012.

M. Seitzer G. Yang J. Schlemper O. Oktay T. Würfl V. Christlein T. Wong R. Mohiaddin D. Firmin J. Keegan et al. "Adversarial and perceptual refinement for compressed sensing mri reconstruction" International Conference on Medical Image Computing and Computer-Assisted Intervention pp. 232-2018.

K. P. Pruessmann M. Weiger M. B. Scheidegger P. Boesiger "SENSE: sensitivity encoding for fast MRI" Magnetic Resonance in Medicine vol. 42 no. 5 pp. 952-962 1999.

M. A. Griswold P. M. Jakob R. M. Heidemann M. Nittka V. Jellus J. Wang B. Kiefer A. Haase "Generalized autocalibrating partially parallel acquisitions (GRAPPA)" Magnetic Resonance in Medicine vol. 47 no. 6 pp. 1202-12002.
Publicado
28/10/2019
SOUZA, Roberto; FRAYNE, Richard. A Hybrid Frequency-domain/Image-domain Deep Network for Magnetic Resonance Image Reconstruction. In: CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 32. , 2019, Rio de Janeiro. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2019 . DOI: https://doi.org/10.5753/sibgrapi.2019.9795.