Independent component analysis for magnetic resonance image analysis

  • Authors:

  • Yen-Chieh Ouyang;Hsian-Min Chen;Jyh-Wen Chai;Cheng-Chieh Chen;Clayton Chi-Chang Chen;Sek-Kwong Poon;Ching-Wen Yang;San-Kan Lee

  • Affiliations:

  • Department of Electrical Engineering, National Chung Hsing University, Taichung, Taiwan;Department of Electrical Engineering, National Chung Hsing University, Taichung, Taiwan;Dept of Radiology, College of Medicine, China Medical Univ, Taichung, Taiwan and School of Medicine, National Yang-Ming Univ, Taipei, Taiwan and Dept of Radiology, Taichung Veterans General Hospit ...;Department of Electrical Engineering, National Chung Hsing University, Taichung, Taiwan;Department of Radiology, Taichung Veterans General Hospital, Taichung, Taiwan and Department of Medical Imaging and Radiological Science, Central Taiwan University of Science and Technology, Taich ...;Division of Gastroenterology, Department of Internal Medicine, Center of Clinical Informatics Research Development, Taichung Veterans General Hospital, Taichung, Taiwan;Computer Center, Taichung Veterans General Hospital, Taichung, Taiwan;Chia-Yi, Veterans Hospital, Chia-Yi, Taiwan

  • Venue:
  • EURASIP Journal on Advances in Signal Processing
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

Independent component analysis (ICA) has recently received considerable interest in applications of magnetic resonance (MR) image analysis. However, unlike its applications to functional magnetic resonance imaging (fMRI) where the number of data samples is greater than the number of signal sources to be separated, a dilemma encountered in MR image analysis is that the number of MR images is usually less than the number of signal sources to be blindly separated. As a result, at least two or more brain tissue substances are forced into a single independent component (IC) in which none of these brain tissue substances can be discriminated from another. In addition, since the ICA is generally initialized by random initial conditions, the final generated ICs are different. In order to resolve this issue, this paper presents an approach which implements the over-complete ICA in conjunction with spatial domain-based classification so as to achieve better classification in each of ICA-demixed ICs. In order to demonstrate the proposed over-complete ICA, (OC-ICA) experiments are conducted for performance analysis and evaluation. Results show that the OC-ICA implemented with classification can be very effective, provided the training samples are judiciously selected.