Reconstruction of cardiac cine MR images using analytic image and neural networks

A reconstruction method for cardiac cine magnetic resonance images is proposed that is based on the combined use of the notion of analytic image and neural network based learning. The analytic image is used to exploit spectral or k-space information and the neural network for a better estimation of missing temporal information. The results show that the proposed approach allows a 4-factor reduction of the data acquisition time in cardiac cine imaging while keeping a good image reconstruction quality with preserved myocardial border sharpness and spatial resolution.

[1]  Pierre Croisille,et al.  Cardiac and respiratory double self‐gated cine MRI in the mouse at 7 T , 2006, Magnetic resonance in medicine.

[2]  Teuvo Kohonen,et al.  Self-Organizing Maps, Third Edition , 2001, Springer Series in Information Sciences.

[3]  Patrick Clarysse,et al.  Spatio-temporal Summarizing Method of Periodic Image Sequences with Kohonen Maps , 2008, ICANN.

[4]  Peter Boesiger,et al.  k‐t BLAST and k‐t SENSE: Dynamic MRI with high frame rate exploiting spatiotemporal correlations , 2003, Magnetic resonance in medicine.

[5]  Jürgen Gieseke,et al.  Sensitivity encoding for fast MR imaging of the brain in patients with stroke. , 2003, Radiology.

[6]  X Hu,et al.  Continuous Update with Random Encoding (CURE): A New Strategy for Dynamic Imaging , 1995, Magnetic resonance in medicine.

[7]  O. Haraldseth,et al.  K‐space substitution: A novel dynamic imaging technique , 1993, Magnetic resonance in medicine.

[8]  M Zaitsev,et al.  Shared k‐space echo planar imaging with keyhole , 2001, Magnetic resonance in medicine.

[9]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[10]  B. Hiba,et al.  Cardiac Cine MR Reconstruction From Partial k-Space Using the Notion of Analytic Image , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[11]  R Frayne,et al.  Time‐resolved contrast‐enhanced 3D MR angiography , 1996, Magnetic resonance in medicine.

[12]  M Suga,et al.  Keyhole method for high‐speed human cardiac cine MR imaging , 1999, Journal of magnetic resonance imaging : JMRI.

[13]  X Hu,et al.  Reduction of field of view for dynamic imaging , 1994, Magnetic resonance in medicine.

[14]  N J Pelc,et al.  Unaliasing by Fourier‐encoding the overlaps using the temporal dimension (UNFOLD), applied to cardiac imaging and fMRI , 1999, Magnetic resonance in medicine.

[15]  Jeffrey Tsao,et al.  On the UNFOLD method , 2002, Magnetic resonance in medicine.

[16]  Isabelle E. Magnin,et al.  Magnetic resonance image reconstruction using analytic image representation , 2007 .

[17]  J. J. van Vaals,et al.  “Keyhole” method for accelerating imaging of contrast agent uptake , 1993, Journal of magnetic resonance imaging : JMRI.

[18]  Samuel Kaski,et al.  Self organization of a massive document collection , 2000, IEEE Trans. Neural Networks Learn. Syst..