MRI brain tissue classification using unsupervised optimized extenics-based methods. (February 2017)

• Record Type: Journal Article
• Authors: Chen, Ruey-Maw; Yang, Sheng-Chih; Wang, Chuin-Mu
• Is Part Of: Computers & electrical engineering. Volume 58(2017)
• Page Start: 489
• Page End: 501
• Publication Date: 2017-02
• Subjects: MRI -- Imaging classification -- Extenics -- PSO -- TGP; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2017.01.018
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: MRI has been a rather important imaging technique in clinical diagnosis in recent years. In particular, brain parenchyma classification and segmentation of normal and pathological tissue is the first step of addressing a wide range of clinical problems. Extenics-based methods are applied in this study for MRI brain tissue classification. Initially, the standard deviation target generation process is employed to select the center point of the extenics-based correlation function without supervision. Then particle swarm optimization is used to modify the extenics-based correlation function. In subsequence, the modified extenics-based correlation function is employed to perform classification using individual images to present the gray matter, white matter and cerebral spinal fluid in the brain. Therefore the proposed method reduce the burden of physicians from huge amounts of multi-spectral information in MR images to make diagnostic work more efficient and more accurate.