ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

Abnormality Detection in Kidney on FPGA Implementation using an Improved Algorithm

Journal: International Journal of Information Technology and Mechanical Engineering (IJITME) (Vol.5, No. 1)

Publication Date:

Authors : ; ;

Page : 1-15

Keywords : Chronic Kidney Disease; Acute Kidney Injury; Ultrasound Imaging; Standard Median Filter; Adaptive K; Statistical and Texture; Artificial Neural Network;

Source : Downloadexternal Find it from : Google Scholarexternal


The kidney diseases can be grouped into two main stages namely Chronic Kidney Diseases (CKD) and Acute Kidney Injury (AKI). The prevalence of chronic kidney diseases will gradually increase if they are not properly treated. It may initiate serious health hazards namely diabetes, blood pressure, pulmonary hypertension and other cardio vascular diseases. Ultrasound imaging technique plays a crucial role in emergency diagnostic method. It is widely used due to its noninvasive inexpensive availability and non-radiation exposure. The main intention of this work is the automatic detection and classification of various diseases such as stone, cyst and cancer masses present in the pelvic region of the kidney. To solve the contradiction between the noise reducing effect and complexity of the time of the standard median filter algorithm, this paper used an improved median filter algorithm. This paper focuses on a 3x3 image window filtering in which the sorting network of the filter should be able to produce the desired result. The hardware result showed that this proposed algorithm has better output result as compared to wavelet filter. It has a good application prospect in real-time image processing. For this research work three main methods are proposed. The first method employs the segmentation using adaptive K means. The second method is feature extraction using statistical and texture. The final method is the modeling of various kidney diseases using artificial neural network.

Last modified: 2019-01-29 15:52:07