Linear Dynamic Sparse Modelling for functional MR imaging

详细信息    查看全文

• 作者：Shulin Yan ; Lei Nie ; Chao Wu ; Yike Guo
• 关键词：Linear Dynamic Sparse Modelling ; Kalman filter ; Sparse Bayesian Learning ; Mutual information
• 刊名：Brain Informatics
• 出版年：2014
• 出版时间：December 2014
• 年：2014
• 卷：1
• 期：1-4
• 页码：11-18
• 全文大小：597KB
• 参考文献：1.Huettel SA, Song AW, McCarthy G (2004) Functional magnetic resonance imaging, vol 1. Sinauer Associates, Sunderland
  2.Lustig M, Donoho D, Pauly JM (2007) Sparse MRI: the application of compressed sensing for rapid MR imaging. Magn Reson Med 58(6):1182鈥?195CrossRef
  3.Donoho DL (2006) Compressed sensing. IEEE Trans Inf Theory 52(4):1289鈥?306CrossRef MATH MathSciNet
  4.Tipping ME (2001) Sparse Bayesian learning and the relevance vector machine. J Mach Learn Res 1:211鈥?44MATH MathSciNet
  5.Gamper U, Boesiger P, Kozerke S (2008) Compressed sensing in dynamic MRI. Magn Reson Med 59(2):365鈥?73CrossRef
  6.Wakin MB, Laska JN, Duarte MF, Baron D, Sarvotham S, Takhar D, Kelly KF, Baraniuk RG (2006) An architecture for compressive imaging. In: IEEE international conference on image processing, 2006, IEEE, pp 1273鈥?276
  7.Kanevsky D, Carmi A, Horesh L, Gurfil P, Ramabhadran B, Sainath TN (2010) Kalman filtering for compressed sensing. In: 13th conference on information fusion (FUSION), 2010, IEEE, pp 1鈥?
  8.Lu W, Vaswani N (2009) Modified compressive sensing for real-time dynamic MR imaging. In: 16th IEEE international conference on image processing (ICIP), 2009, IEEE, pp 3045鈥?048
  9.Vaswani N (2008) Kalman filtered compressed sensing. In: 15th IEEE international conference on image processing, 2008, ICIP 2008, IEEE, pp 893鈥?96
  10.Liu Dd, Liang D, Liu X, Zhang Yt (2012) Under-sampling trajectory design for compressed sensing MRI. In: Annual international conference of the IEEE engineering in medicine and biology society (EMBC), 2012, IEEE, pp 73鈥?6
  11.Ravishankar S, Bresler Y (2011) Adaptive sampling design for compressed sensing MRI. In: Annual international conference of the IEEE engineering in medicine and biology society, EMBC, 2011, IEEE, pp 3751鈥?755
  12.Seeger M, Nickisch H, Pohmann R, Sch枚lkopf B (2010) Optimization of k-space trajectories for compressed sensing by Bayesian experimental design. Magn Reson Med 63(1):116鈥?26
  13.Filos J, Karseras E, Dai W, Yan S (2013) Tracking dynamic sparse signals with hierarchical Kalman filters: a case study. In: 18th international conference on digital signal processing (DSP), 2013, IEEE, pp 1鈥?
  14.Chang HS, Weiss Y, Freeman WT (2009) Informative sensing. arXiv:鈥?901.鈥?275
  15.Lu W, Li T, Atkinson IC, Vaswani N (2011) Modified-cs-residual for recursive reconstruction of highly undersampled functional MRI sequences. In: 18th IEEE international conference on image processing (ICIP), 2011, IEEE, pp 2689鈥?692
  16.Kyriazis GA, Martins MA, Kalid RA (2012) Bayesian recursive estimation of linear dynamic system states from measurement information. Measurement 45(6):1558鈥?563CrossRef
  17.Seeger M, Wipf DP (2010) Variational Bayesian inference techniques. IEEE Signal Process Mag 27(6):81鈥?1
  18.Shamaiah M, Banerjee S, Vikalo H (2010) Greedy sensor selection: leveraging submodularity. In: 49th IEEE conference on decision and control (CDC), 2010, IEEE, pp 2572鈥?577
  19.Cohen MS, Schmitt F (2012) Echo planar imaging before and after fMRI: a personal history. Neuroimage 62(2):652鈥?59CrossRef
  20.Glover GH (2012) Spiral imaging in fMRI. Neuroimage 62(2):706鈥?12CrossRef MathSciNet
  21.Kannengiesser S, Brenner A, Noll T (2000) Accelerated image reconstruction for sensitivity encoded imaging with arbitrary k-space trajectories. In: Proceedings of the 8th annual meeting of the ISMRM
  22.Kyriakos WE, Panych LP, Kacher DF, Westin CF, Bao SM, Mulkern RV, Jolesz FA (2000) Sensitivity profiles from an array of coils for encoding and reconstruction in parallel (space rip). Magn Reson Med 44(2):301鈥?08CrossRef
  23.Lustig M, Lee JH, Donoho DL, Pauly JM (2005) Faster imaging with randomly perturbed, under-sampled spirals and l1 reconstruction. In: Proceedings of the 13th annual meeting of ISMRM, Miami Beach, p 685
  24.Weiger M, Pruessmann KP, 脰sterbauer R, B枚rnert P, Boesiger P, Jezzard P (2002) Sensitivity-encoded single-shot spiral imaging for reduced susceptibility artifacts in bold fMRI. Magn Reson Med 48(5):860鈥?66CrossRef
  
• 作者单位：Shulin Yan (1)
  Lei Nie (1) (2)
  Chao Wu (1)
  Yike Guo (1)
  
  1. Data Science Institute, Imperial College London, London, UK
  2. Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
  
• 刊物类别：Artificial Intelligence (incl. Robotics); Health Informatics; Neurosciences; Computation by Abstract
• 刊物主题：Artificial Intelligence (incl. Robotics); Health Informatics; Neurosciences; Computation by Abstract Devices; Cognitive Psychology;
• 出版者：Springer Berlin Heidelberg
• ISSN：2198-4026

文摘

The reconstruction quality of a functional MRI sequence is determined by reconstruction algorithms as well as the information obtained from measurements. In this paper, we propose a Linear Dynamic Sparse Modelling method which is composed of measurement design and reconstruction processes to improve the image quality from both aspects. This method models an fMRI sequence as a linear dynamic sparse model which is based on a key assumption that variations of functional MR images are sparse over time in the wavelet domain. The Hierarchical Bayesian Kalman filter which follows the model is employed to implement the reconstruction process. To accomplish the measurement design process, we propose an Informative Measurement Design (IMD) method. The IMD method addresses the measurement design problem of selecting k feasible measurements such that the mutual information between the unknown image and measurements is maximised, where k is a given budget and the mutual information is extracted from the linear dynamic sparse model. The experimental results demonstrated that our proposed method succeeded in boosting the quality of functional MR images. Keywords Linear Dynamic Sparse Modelling Kalman filter Sparse Bayesian Learning Mutual information