Rough Set and Multi-thresholds based Seeded Region Growing Algorithm for Image Segmentation

The segmentation of brain tumor from MRI (Magnetic Resonance Imaging) scan images is still demanding because it exhibits complex characteristics such as high diversity in tumor appearance and ambiguous tumor boundaries. In this paper, multi-thresholds and rough set-based region growing method for MRI brain image is been proposed as a fully automatic technique. The extracted Region of Interest (ROI) from the proposed method helps in improving the performance of the overall proposed system. The consequent features are been extracted from MRI images by applying the suitable feature extraction techniques to classify the tumor images from normal images. The results of various segmentation techniques are been compared and are proved experimentally. The performance is been evaluated based on the Jaccard distance and DICE coefficient, and it has been found that the proposed approach fairs better with high similarity and less computation time. The overall system achieved 98% accuracy.

[1]  Rudolf Konrad Fruhwirth,et al.  A Statistical Feature-Based Approach for Operations Recognition in Drilling Time Series , 2012, CISIM 2012.

[2]  Abderrahmane Sbihi,et al.  A Combined Method Of Fractal And GLCM Features For MRI And CT Scan Images Classification , 2014, ArXiv.

[3]  RoyPayel,et al.  Image Segmentation Using Rough Set Theory , 2014 .

[4]  Nilanjan Dey,et al.  Image Segmentation Using Rough Set Theory: A Review , 2014, Int. J. Rough Sets Data Anal..

[5]  E. VenkateswaraReddy,et al.  Image Segmentation using Rough Set based Fuzzy K-means Algorithm , 2013 .

[6]  R. S. Rajesh,et al.  A Study on Rough Set Theory for Medical Image Segmentation , 2009 .

[7]  Shusaku Tsumoto,et al.  Rough representation of a region of interest in medical images , 2005, Int. J. Approx. Reason..

[8]  K. S. Patnaik,et al.  Analysis of Clustering Algorithms for MR Image Segmentation using IQI , 2012 .

[9]  D. Anithadevi,et al.  A hybrid approach based segmentation technique for brain tumor in MRI Images , 2016, ArXiv.

[10]  Irfan Mehmood,et al.  Bayesian Classification Using DCT Features for Brain Tumor Detection , 2010, KES.

[11]  Tanuja Pandurang Shewale,et al.  Detection of Brain Tumor Based On Segmentation Using Region Growing Method , 2016 .

[12]  Zhengqin Li,et al.  Automatic Image Cropping: A Computational Complexity Study , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Pradeep M. Patil,et al.  Detection and Classification of Brain Tumors , 2015 .