Classification in Chronic Kidney Disease by Nakagami Distribution and Local Binary Pattern

• Main Authors: Lee, Wei-Shan, 李偉聖
• Other Authors: Hsieh, Jun-Wei
• Format: Others
• Language: zh-TW
• Published: 2014
• Online Access: http://ndltd.ncl.edu.tw/handle/84007010859684925386

碩士 === 國立臺灣海洋大學 === 資訊工程學系 === 103 === Ultrasound imaging can provide radiation-free, non-invasive, low cost, and convenient to detect diseases and thus becomes an incontestable vital tool for clinical diagnosis. However, speckle effect makes it very noisy and thus reduces its overall diagnostic abilities and diversities to detect different kinds of diseases. This paper develops a real time system to analyze chronic kidney disease (CKD) using only Ultrasound images. As we know, this is the first work to analyze CKD stages of patients directly from ultrasound images without using any blood examination such as Creatinine index. To build the scoring index for CKD stage classification, this paper uses Nakagami distribution and Local Binary Pattern (LBP) to model the scattering properties of CKD ultrasound images. In addition, we find the age distribution is also important for CKD stage analysis. After integration, a codebook concept is adopted to extract important visual codes to describe the texture and scattering characteristics of each CKD stage. Then, we build a strong CKD stage classifier via SVM for CKD stage prediction and classification. Experimental results demonstrate the sensitivity and specificity of this system up to 97.40% and 86.67%, respectively.