Detecting brain activations by constrained non-negative matrix factorization from task-related BOLD fMRI

Non-negative Matrix Factorization (NMF) has previously been shown to be a useful decomposition for multivariate data. In this paper, we introduce this new technique to the field of fMRI data analysis. In order to make the representation suitable for task-related brain activation detection, we imposed some additional constraints, and defined an improved contrast function. We deduced the update rules and proved the convergence of the algorithm. In the procedure, the number of factors was determined by visual assessment. We studied 8 healthy right-handed adult volunteers by a 3.0T GE Signa scanner. A block design motor paradigm (bilateral finger tapping) stimulated the blood oxygenation level-dependent (BOLD) response. Gradient Echo EPI sequence was utilized to acquire BOLD contrast functional images. With this constrained NMF (cNMF) we could obtain major activation components and the corresponding time courses, which showed high correlation with the reference function (r>0.7). The results showed that our method would be feasible for detection brain activations from task-related fMRI series.

[1]  Stan Z. Li,et al.  Learning spatially localized, parts-based representation , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[2]  V D Calhoun,et al.  Spatial and temporal independent component analysis of functional MRI data containing a pair of task‐related waveforms , 2001, Human brain mapping.

[3]  D. Tank,et al.  Brain magnetic resonance imaging with contrast dependent on blood oxygenation. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[4]  L. K. Hansen,et al.  On Clustering fMRI Time Series , 1999, NeuroImage.

[5]  Vince D. Calhoun,et al.  ICA of functional MRI data: an overview. , 2003 .

[6]  James V. Stone.  Independent component analysis: an introduction , 2002, Trends in Cognitive Sciences.

[7]  Christian F. Beckmann,et al.  PROBABILISTIC ICA FOR FMRI - NOISE AND INFERENCE , 2003 .

[8]  Stefan M. Wild.  Seeding Non-Negative Matrix Factorizations with the Spherical K-Means Clustering , 2003 .

[9]  T. Adali,et al.  Latency (in)sensitive ICA Group independent component analysis of fMRI data in the temporal frequency domain , 2003, NeuroImage.

[10]  Chung-Chih Lin,et al.  Model Free Functional MRI Analysis Using Kohonen Clustering Neural Network , 1999, IEEE Trans. Medical Imaging.

[11]  Vince D. Calhoun,et al.  Complex ICA for fMRI analysis: performance of several approaches , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[12]  S Makeig,et al.  Analysis of fMRI data by blind separation into independent spatial components , 1998, Human brain mapping.

[13]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[14]  Alan C. Evans,et al.  A General Statistical Analysis for fMRI Data , 2000, NeuroImage.

[15]  Alan C. Evans,et al.  A general statistical analysis for fMRI data , 2000, NeuroImage.

[16]  James V. Stone,et al.  Spatiotemporal Independent Component Analysis of Event-Related fMRI Data Using Skewed Probability Density Functions , 2002, NeuroImage.

[17]  R. Turner,et al.  Dynamic magnetic resonance imaging of human brain activity during primary sensory stimulation. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[18]  Kai-Hsiang Chuang,et al.  Model-free functional MRI analysis using Kohonen clustering neural network and fuzzy C-means , 1999, IEEE Transactions on Medical Imaging.

[19]  V D Calhoun,et al.  Independent component analysis of fMRI data in the complex domain , 2002, Magnetic resonance in medicine.

[20]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.