Abstract

In this paper, we present a proposed algorithm to classify brain MRI as tumor-free or tumor present. For computing difference between normal and abnormal MR images, a set of features is calculated. The number of features of the original feature set is reduced by rough set based K-means algorithm and classification of the dataset into tumor-free or tumor-present category has been done by support vector machine (SVM). The proposed algorithm gives better classification result for a smaller set of training dataset.

BibTeX Citation

@INPROCEEDINGS{8125826,
  author={Halder, Amiya and Dobe, Oyendrila},
  booktitle={2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI)}, 
  title={Rough K-means and support vector machine based brain tumor detection}, 
  year={2017},
  volume={},
  number={},
  pages={116-120},
  doi={10.1109/ICACCI.2017.8125826}}