Machine learning approach to track the progress of lesions using Change Detection

Authors

  • Ankita Mitra Department of Electronics and Communication, National Institute of Technology
  • Arunava De Department of Information Technology, Dr. B.C. Roy Engineering College
  • Anup Kumar Bhattacharjee Department of Electronics and Communication, National Institute of Technology

Keywords:

Region of Interest, Magnetic Resonance Imaging, Multi Resolution Wavelet Analysis, Change Detection, Peaks over Threshold,Wavelet Thresholding.

Abstract

Brain MR image requires analysis of complex data. In this article use of machine learning approaches together with the Change detection algorithms is aimed at identifying changes in sets of images or image sequences at different times. In other words it is the process of identifying the changes in a state of an object over time. The phenomena of change detection are used to detect the progress of lesions in MR Images. Two class classification models are used to identify the object, which are the lesions and the background of the MR image. De-noising of MR image is done using Peaks over Threshold for Shrinking the Wavelet coefficients. Change detection algorithms are used on a sequence of MR images to find the extent of progression of lesions in an patient.

Downloads

Download data is not yet available.

Downloads

Published

2014-01-01

How to Cite

Ankita Mitra, Arunava De, & Anup Kumar Bhattacharjee. (2014). Machine learning approach to track the progress of lesions using Change Detection. Journal of Network and Innovative Computing, 2, 8. Retrieved from https://cspub-jnic.org/index.php/jnic/article/view/47

Issue

Section

Original Article