This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
|
||||||||
|
Paper Details
Paper Title
Renal Disease Prediction By Feature Extraction Techniques Using CT Scan Images
Authors
  M.Fathima,  Mrs.R.karthiyayini
Abstract
Renal disease is the very critical disease spreading nowadays in the wholeworld due to the change in our life style, including food habits, environment, etc.,. Kidney Disease is currently considered as the general problem in recent days. Data miningis a interdisciplinary field used to extract the hidden patterns for critical resolution making in any discipline. This field consists of plenty of techniques and algorithms for developing data mining systems for any specific domain. The scope of this project is to anticipate Chronic renal Disease prediction using the techniques of classification algorithms SVM and Naïve Bayes. Final stage of renal disease and kidney transplantation remain the most definitive renal end points, thus the project contribution is focused on quality of human life. Several computer scientists have been proposing new algorithms, combination of certain methods and system based steps for the medical image processing, although many ways are suggested that accuracy of the prediction still requires modifications. The Image preprocessing are done in MATLAB using Gray conversion, BW image processing, Gaussian filtering and Morphological operations in the CT Scan images for renal disease analysis.
Keywords- Image segmentation,Chronic Kidney Disease (CKD),SVM and Naïve Bayes.
Publication Details
Unique Identification Number - IJEDR1802093Page Number(s) - 528-533Pubished in - Volume 6 | Issue 2 | April 2018DOI (Digital Object Identifier) -    Publisher - IJEDR (ISSN - 2321-9939)
Cite this Article
  M.Fathima,  Mrs.R.karthiyayini,   "Renal Disease Prediction By Feature Extraction Techniques Using CT Scan Images", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.6, Issue 2, pp.528-533, April 2018, Available at :http://www.ijedr.org/papers/IJEDR1802093.pdf
Article Preview
|
|
||||||
|