The Diffusion Weighted Imaging (DWI) technique can be utilized to investigate a variety of diseases. We propose an automated system which assists the diagnosis of metabolic brain diseases clinically. In this study, DWI images are preprocessed and exponential Apparent Diffusion Coefficient (eADC) Images are produced. The eADC images are later brain extracted and normalized to a standard brain atlas. Subsequently, we utilized wavelets to denoise the eADC images. The images are rectified, thresholded and conspicuous abnormal regions are identified. Abnormal regions constitute the features that will be used by a fuzzy relational classifier in order to categorize the diseases. The sensitivity, positive predictivity and specificity of 60%, 60% and 93.33%, respectively in detecting metabolic brain diseases have been achieved.
机构:
Yonsei Univ, Sch Elect & Elect Engn, Seoul 120749, South Korea
Univ Calif San Francisco, Dept Radiol, San Francisco, CA 94143 USAYonsei Univ, Sch Elect & Elect Engn, Seoul 120749, South Korea
Kim, Dong-Hyun
Chung, SungWon
论文数: 0引用数: 0
h-index: 0
机构:
Univ Calif San Francisco, Dept Radiol, San Francisco, CA 94143 USAYonsei Univ, Sch Elect & Elect Engn, Seoul 120749, South Korea
Chung, SungWon
Vigneron, Daniel B.
论文数: 0引用数: 0
h-index: 0
机构:
Univ Calif San Francisco, Dept Radiol, San Francisco, CA 94143 USAYonsei Univ, Sch Elect & Elect Engn, Seoul 120749, South Korea
Vigneron, Daniel B.
Barkovich, A. James
论文数: 0引用数: 0
h-index: 0
机构:
Univ Calif San Francisco, Dept Radiol, San Francisco, CA 94143 USAYonsei Univ, Sch Elect & Elect Engn, Seoul 120749, South Korea
Barkovich, A. James
Glenn, Orit A.
论文数: 0引用数: 0
h-index: 0
机构:
Univ Calif San Francisco, Dept Radiol, San Francisco, CA 94143 USAYonsei Univ, Sch Elect & Elect Engn, Seoul 120749, South Korea