ABSTRACT
Echo-planar imaging suffers from Nyquist ghost (i.e., N/2 ghost) because of the imperfection of the gradient system and gradient delays. The phase mismatch between even and odd echoes can be eliminated by an extra reference scan without the phase encoding. However, due to the non-linear and time-varying local magnetic field changes or movement of the patients, the reference-based methods may have incorrect correction results. Other correction methods like parallel imaging reconstruction may suffer from the image noise amplification and signal-to-noise ratio penalty. In this study, a deep learning method is proposed to eliminate the phase error in k-space and correct the mismatch between even and odd echoes without reference scan and SNR penalty. The Fourier transform layer is introduced into the conventional U-Net structure, and the distortion-free images are directly reconstructed from the k-space EPI data. Turbo spin echo data and single-shot EPI data are tested using this network. The results show that this method has a good performance in ghost correction, and the ghost-to-signal ratio is effectively reduced compared to other state-of-the-art correction methods. The proposed deep learning method is reference-free and effective to correct Nyquist ghost in EPI, and can also combine with parallel imaging to achieve additional acceleration.
- Xiang, Q.-S., & Ye, F. Q. (2007). Correction for geometric distortion and N/2 ghosting in EPI by phase labeling for additional coordinate encoding (PLACE). Magnetic Resonance in Medicine, 57(4), 731--741. DOI:http://dx.doi.org/10.1002/mrm.21187Google Scholar
- Lee J., Jin K. H., and Ye J. C. 2016. Reference Free Single-Pass EPI Nyquist Ghost Correction Using Annihilating Filter-Based Low Rank Hankel Matrix (ALOHA). Magnetic Resonance in Medicine 76 (2016), 1775--1789. DOI: http: //dx.doi.org/10.1002/mrm.26077Google ScholarCross Ref
- Xie V. B., Lyu M., Liu Y., Feng Y., and Wu E. X. 2018. Robust EPI Nyquist Ghost Removal by Incorporating Phase Error Correction With Sensitivity Encoding (PEC-SENSE). Magnetic Resonance in Medicine 79(2018), 943--951. DOI: http://dx.doi.org/10.1002/mrm.26710Google ScholarCross Ref
- Zhu B., Bilgic B., Liao C., Rosen B. R., and Rosen M. S. 2018. Deep learning MR reconstruction with Automated Transform by Manifold Approximation (AUTOMAP) in real-world acquisitions with imperfect training. In Proceedings of the 26th Annual Meeting of ISMRM, Singapore, (2018), p.0572.Google Scholar
- Schlemper J., Oksuz I., Clough J., Duan J., King A. P., Schnabel J. A., Hajnal J. V., and Rueckert D. 2019. dAUTOMAP: Decomposing AUTOMAP to Achieve Scalability and Enhance Performance. In Proceedings of the 27th Annual Meeting of ISMRM, Canada, (2019), 0658.Google Scholar
- Olaf Ronneberger. 2017. Invited Talk: U-Net Convolutional Networks for Biomedical Image Segmentation. Informatik aktuell Bildverarbeitung für die Medizin 2017 (2017), 3--3. DOI:http://dx.doi.org/10.1007/978-3-662-54345-0_3Google Scholar
- Ioffe S., and Szegedy C. 2015. Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv: (2015), 1502.03167.Google Scholar
- Nair V., and Hinton G. E. 2010. Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning, Haifa, Israel. (2010), 807--814.Google Scholar
- Stark H., and Oskoui P. 1989. High-resolution image recovery from image-plane arrays, using convex projections[J]. Journal of the Optical Society of America A Optics & Image Science, 1989, 6(11): 1715 DOI: http: //dx.doi.org/10.1364/josaa.6.001715Google ScholarCross Ref
- http://github.com/tensorflowGoogle Scholar
- http://keras.ioGoogle Scholar
- Walsh D O., Gmitro A F., and Marcellin M W. Adaptive reconstruction of phased array MR imagery[J]. Magnetic resonance in medicine: official journal of the Society of Magnetic Resonance in Medicine / Society of Magnetic Resonance in Medicine, 2000, 43(5):682--690. DOI: http: //dx.doi.org/10.1002/(sici)1522-2594Google Scholar
Index Terms
- Reference-free Correction for the Nyquist Ghost in Echo-planar Imaging using Deep Learning
Recommendations
Automatic Segmentation of the Prostate on 3D CT Images by Using Multiple Deep Learning Networks
ICBBE '18: Proceedings of the 2018 5th International Conference on Biomedical and Bioinformatics EngineeringAutomatic segmentation of the prostate on CT images has many applications in prostate cancer diagnosis and therapy. However, prostate segmentation from CT images is a very challenging task due to the low contrast of soft tissue and the large variations ...
Deep learning techniques in PET/CT imaging: A comprehensive review from sinogram to image space
Highlights- Reviewed DL model approaches used for PET/CT imaging.
- Assessment of the pre-processing techniques for DL models with PET/CT input.
- Addresses existing gaps in the literature and suggestions for future research.
AbstractPositron emission tomography/computed tomography (PET/CT) is increasingly used in oncology, neurology, cardiology, and emerging medical fields. The success stems from the cohesive information that hybrid PET/CT imaging offers, surpassing the ...
Graphical abstractDisplay Omitted
Multiple organ-specific cancers classification from PET/CT images using deep learning
AbstractAs the number of cancer cases increases and the popularity of positron emission tomography/computed tomography (PET/CT), an automated cancer screening system that can assist radiologists is desired. The existing methods based on PET/CT images are ...
Comments