An Automated Segmentation Algorithm for Detection of MENINGIOMA and GBM using Reformed Self-Organizing Maps

B Hema Kumar, R Malathi, R Ananda Natarajan
2017 Journal of Advanced Computing  
The MRI Brain tumor segmentation can be performed by different algorithms that are based on a wide range of principles. In case of a high manual interaction, the process is time consuming and it introduces a high intra-subject and inter-subject variability due to the personal subjectivity. Tumor segmentation from MRI images is a challenging task. Due to the complex overlay of images in MRI, an automated segmentation and decision based on segmentation would be difficult. We propose an automated
more » ... opose an automated segmentation algorithm for MRI images based on typical radiological signs using Reformed Self-Organizing Maps (RSOM). The performance of the automated segmentation method was evaluated using seven performance indices and we found our RSOM proposed method was having high J coefficient, high F measure, better Accuracy & better Quality of segmentation.
doi:10.7726/jac.2017.1004 fatcat:lf3mpz4k7rb5ldi2qjkdqkfksi