Abstract
This paper proposes a method of extending the optimal linear transformation (OLT), an image analysis technique of feature space, from magnetic resonance imaging (MRI) to functional magnetic resonance imaging (fMRI) so as to improve the activation detection performance over conventional approaches of fMRI analysis. The method was: (1) ideal hemodynamic responses for different stimuli were generated by convolving the theoretical hemodynamic response model with the stimulus timing, (2) considering the ideal hemodynamic responses as hypothetical signature vectors for different activity patterns of interest, OLT was used to extract the features of fMRI data. The resultant feature space had particular geometric clustering properties. It was then classified into different groups, each pertaining to an activity pattern of interest; the applied signature vector for each group was obtained by averaging, (3) using the applied signature vectors, OLT was applied again to generate fMRI composite images with high SNRs for the desired activity patterns. Simulations and a blocked fMRI experiment were employed to validate the proposed method. The simulation and the experiment results indicated the proposed method was capable of improving some conventional methods to be more sensitive to activations, having strong contrast between activations and inactivations, and being more valid for complex activity patterns.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Burke D, Murphy K, Garavan H, Reilly R (2004) Pattern recognition approach to the detection of single-trial event-related functional magnetic resonance images. Med Biol Eng Comput 42(5):604–609
Chuang K-H, Chiu M-J, Lin C-C, Chen J-H (1999) Model-free functional MRI analysis using Kohonen clustering neural network and fuzzy C-means. IEEE Trans Med Imaging 18(12):1117–1128
Çiftçi K, Sankur B, Kahya YP, Akın A (2008) Constraining the general linear model for sensible hemodynamic response function waveforms. Med Biol Eng Comput 46(8):779–787
Cohen MS (1997) Parametric analysis of fMRI data using linear systems methods. Neuroimage 6(2):93–103
Cox RW (1996) AFNI: software for analysis and visualization of functional magnetic resonance neuroimages. Comput Biomed Res 29(3):162–173
de Maziere PA, van Hulle MM (2007) fMRI bold signal analysis using a novel nonparametric statistical method. J Magn Reson 185(1):138–151
Dimitriadou E, Barth M, Windischberger C, Hornik K, Moser E (2004) A quantitative comparison of functional MRI cluster analysis. Artif Intell Med 31(1):57–71
Friston KJ, Holmes AP, Worsley KJ, Poline JB, Frith C, Frackowiak RSJ (1995) Statistical parametric maps in functional imaging: a general linear approach. Hum Brain Mapp 2:189–210
Friston KJ, Stephan KE, Lund TE, Morcom A, Kiebel SJ (2005) Mixed-effects and fMRI studies. Neuroimage 24:244–252
Gao J (2003) Iterative temporal clustering analysis for the detection of multiple response peaks in fMRI. Magn Reson Imaging 21(1):51–53
Glover GH (1999) Deconvolution of impulse response in event-related BOLD fMRI. Neuroimage 9:416–429
Goutte C, Hansen LK, Liptrot MG, Rostrup E (2001) Feature-space clustering for fMRI meta-analysis. Hum Brain Mapp 13:165–183
Hellera R, Stanleyb D, Yekutielia D, Rubinb N, Benjaminia Y (2006) Cluster-based analysis of FMRI data. Neuroimage 33(2):599–608
Krishnan K, Atkins MS (1998) Segmentation of multiple sclerosis lesions in MRI—an image analysis approach. Proc SPIE Int Symp Med 3338:1106–1116
Lai S-H, Fang M (1998) Novel local PCA-based method for detecting activation signals in fMRI. Proc SPIE 3337:327–338
Lange O, Meyer-Baese A, Hurdal M, Foo S (2006) A comparison between neural and fuzzy cluster analysis techniques for functional MRI. Biomed Signal Process Control 1(3):243–252
McKeown MJ, Sejnowski TJ (1998) Independent component analysis of fMRI data: examining the assumptions. Hum Brain Mapp 6(5–6):368–372
Meyer FG, Chinrungrueng J (2003) Features selection for clustering of fMRI data. Proc SPIE 5207:426–434
Patriarche JW, Erickson B (2007) Part 1. Automated change detection and characterizations in serial MR studies of brain-tumor patients. J Digital Imaging 20(3):203–222
Pham DL, Xu C, Prince JL (2000) Current methods in medical image segmentation. Annu Rev Biomed Eng 2:315–337
Salih QA, Ramli AR, Mahmud R, Wirza R (2005) Brain white and gray matter anatomy of MRI segmentation based on tissue evaluation. Medscape Gen Med 7(2):1
Soltanian-Zadeh H, Windham JP, Peck DJ, Yagle AE (1992) A comparative analysis of several transformations for enhancement and segmentation of magnetic resonance image scene sequence. IEEE Trans Med Imaging 11(3):302–318
Soltanian-Zadeh H, Windham JP, Peck DJ (1996) Optimal linear transformation for MRI feature extraction. IEEE Trans Med Imaging 15(6):749–767
Soltanian-Zadeh H, Peck DJ, Hearshen DO, Lajiness-O’Neill RR (2004) Model-independent method for fMRI analysis. IEEE Trans Med Imaging 23(3):285–296
Wang C-M, Chen C-C, Chung Y-N et al (2003) Detection of spectral signatures in multispectral MR images for classification. IEEE Trans Med Imaging 22(1):50–61
Worsley KJ, Marrett S, Neelin P, Vandal AC, Friston KJ, Evans AC (1996) A unified statistical approach or determining significant signals in images of cerebral activation. Hum Brain Mapp 4:58–73
Worsley KJ, Liao CH, Aston J, Petre V, Duncan GH, Morales F, Evans AC (2002) A general statistical analysis for fMRI data. Neuroimage 15:1–15
Acknowledgments
The authors would like to thank Dr. Margot J. Taylor for her contributions to this paper. This work was partly supported by the Outstanding Young Scientist Foundation of Shandong Province under the Grant 2005BS01006.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Sun, F., Morris, D. & Babyn, P. The optimal linear transformation-based fMRI feature space analysis. Med Biol Eng Comput 47, 1119–1129 (2009). https://doi.org/10.1007/s11517-009-0504-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-009-0504-6