Application of Extenics Approach in MRI Classification

• Main Authors: Ren-Zhi Lan, 藍仁志
• Other Authors: Chuin-Mu Wang
• Format: Others
• Language: zh-TW
• Online Access: http://ndltd.ncl.edu.tw/handle/08140747841324887531

碩士 === 國立勤益技術學院 === 資訊與電能科技研究所 === 93 === Along with rapid technological advancement in recent years, Magnetic Resonance Image (MRI) has been widely used for clinical applications. With the ability of scanning the same section by multiple frequencies, Magnetic Resonance Image (MRI) makes it possible to generate several images on the same section. Despite of accessible abundant information, MRI also makes it more difficult to judge the location of every tissue. Moreover, Magnetic Resonance Image (MRI) will complicate the judgment due to strong noise. In order to resolve this problem, this paper endeavors to classify them via the help of Extension(Extenics, Extension Theory), which can separate the blocks efficiently so as to reduce the noise effect upon tissues. This paper has demonstrated satisfactory noise-proof features of extension.Furthermore, Extension Theory along with Target Generation Process has become an unsupervision method, which aims to improve the availability of extension on medical image. To demonstrate the advantages of Extension Theory, ROC(Receiver Operating Curve) is considered as a judgment method, whereby obtaining experimental data of Extension and FCM (Fuzzy c-means)for subsequent comparison. It has thus proved that Extension is superior to FCM in terms of classification and noise immunity.