The week's pick
Random Articles
Reseach Article
Automatic Detection for Healthy and Unhealthy Kidneys on Abdominal CT Images using Machine Learning Algorithm
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 173 - Number 2 |
| Year of Publication: 2017 |
| Authors: Israt Jahan Tulin |
10.5120/ijca2017915247
|
Israt Jahan Tulin . Automatic Detection for Healthy and Unhealthy Kidneys on Abdominal CT Images using Machine Learning Algorithm. International Journal of Computer Applications. 173, 2 ( Sep 2017), 7-10. DOI=10.5120/ijca2017915247
Abstract
In this paper, we have proposed a machine learning (Support Vector Machine) approach for detecting healthy and unhealthy kidneys in CT (Computed Tomography) images. At first, kidney region have been segmented from the abdomen area using region growing algorithm. After successful segmentation, the kidney region is extracted and it is given to Support Vector Machine algorithm for the final detection of which kidney is healthy and unhealthy. Our proposed approach consists of training process and testing process. In training process we train our algorithm with the CT images of healthy kidney and unhealthy kidney. In testing process our algorithm detect healthy and unhealthy kidneys from the input images with an accuracy of 73.3%. The proposed algorithm has been implemented in MATLAB and experiment result tested on 70 images downloaded from internet.
References
- E. Supriyanto, Hafizah W.M, Wui Y.J, Arooj A. Automatic Non Invasive Kidney Volume Measurement Based On Ultrasound Image Proceedings of 15th International WSEAS GSCC Multiconferences held in Corfu Island , Greece, July 14- 16,2011 ISBN: 978-1-61804-019-0 Page 387-392
- R. PohleandK.D. Toennies,“Anewapproachformodel-basedadaptive region growing in medical image analysis,” in the 9th Int. Conf. Computer Analysis of Images and Patterns, vol. 2124, Warsaw, Poland, 2001, pp. 238–246.
- R. Pohle and K. D. Toennies, “Segmentation of medical images using adaptive region growing,” in Proc. Int. Soc. Opt. Eng. (SPIE), vol. 4322, 2001, pp. 1337–1346.
- R. Pohle and K. D. Toennies, “Self-learning model-based segmentation of medical images,” Image Process. Commun., vol. 7, pp. 97–113, 2001.
- S.H. Kim,S.W. Yoo,S.J. Kim,J.C. Kim,andJ.W. Park,“Segmentation ofkidneywithoutusingcontrastmediumonabdominalCTimage,”in5th Int. Conf. Signal Processing, vol. 2, Beijing, China, 2000, pp. 1147– 1152.
- S. W. Yoo, J. S. Cho, S. M. Noh, K. S. Shin, and J. W. Park, “Organ segmentation by comparing of gray value portion on abdominal CT image,” in 5th Int. Conf. on Signal Processing, vol. 2, Beijing, China, 2000, pp. 1201–1208.
- M. Kobashi and L. G. Shapiro, “Knowledge-based organ identification from CT images,” Pattern Recogn., vol. 28, pp. 475–491, 1995.
- S.Mavromatis, J.M.Bo, and J.Sequeira, “Medical image segmentation using texture directional features,” in IEEE 23rd Annu. Int. Conf. Eng. Med. Biol. Soc., vol. 3, Istandbul, Turkey, 2001.
- X. Wang, L. He, and W. G. Wee, “Deformable contour method: A constrained optimization approach,” Int. J. Comput. Vision, vol. 59, no. 1, pp. 87–108, 2004.
- B. Tsagaan, A. Shimizu, H. Kobatake, K. Miyakawa, and Y. Hanzawa, “Segmentation of kidney by using a deformable model,” in Int. Conf. Image Processing, vol. 3, Thessaloniki, Greece, 2001, pp. 1059–1062.
- B. Tsagaan,A. Shimizu,H. Kobatake,andK. Miyakawa,“Anautomated segmentation method of kidney using statistical information,” in Proc. Medical Image Computing and Computer Assisted Intervention, vol. 1, 2002, pp. 556–563.
- V. Vapnik, The Nature of Statistical Learning Theory, Springer, 1995.
- C. Cortes and V. Vapnik. Support vector networks. Machine Learning, 20, 1995.
Index Terms
Keywords