Classification of Chronic Kidney Disease Using Doppler Images based on Kurtosis、Curvature and Discrete Wavelet Transform

• Main Authors: Yu-Chi Shih, 石祐齊
• Other Authors: Jun-Wei Hsieh
• Format: Others
• Language: en_US
• Published: 2016
• Online Access: http://ndltd.ncl.edu.tw/handle/9789yx

碩士 === 國立臺灣海洋大學 === 資訊工程學系 === 104 === 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. In the past, we used Estimated Glomerular filtration ratio (eGFR) to classify the stages of renal disease. Now we are attempting to find more efficient and simpler approaches to reduce the cost and errors. 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. Based on the data from clinical diagnosing, we use the ultrasound waveform image to determine the stages of CKD. The features we used to analysis the waveform are Kurtosis, Curvature and Discrete Wavelet Transform. Then, we build a strong CKD stage classifier via SVM for CKD stage prediction and classification. This approach can easily classify the status of the kidney disease in high accuracy. Based on the skill, we can reduce the unnecessary mistakes by the clinical diagnosis, more importantly, save time, efforts and cost.