Classification of Brain Tumor Based On Data Mining Techniques

Information Technology

Image processing techniques are most widely used in medical imaging to identify the affected area through X-ray, CT scan, MRI scan. Image processing is used to detect and identify the inner most portion of the human body. Here we have focused on the brain tumor detection techniques. Major brain tumors are not diagnosed until after symptoms appear. The main objective of the work is to explore various techniques to detect brain tumor using MRI in an efficient way. It has been found that the most of existing methods has ignored the poor quality images like images with noise or poor brightness. Also, tumor detections using MRI images are a challenging task, due to the complex structure of the brain. The methodology includes image preprocessing, image segmentation, the detection and extraction of the tumor zone based on morphological operations. Using K-Means Clustering Algorithm, we can filter the brain tumor of an image. This algorithm is used to detect the range and shape of the tumor in brain MRI images. The tumor is extracted from MRI image and its exact shape and position are determined. The amount of area calculated from the cluster is used to display the size and type of the tumor. Keywords: Pre-processing, Segmentation, Extraction, Classification, Brain Tumor, K-Means Clustering, Feature Selection.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.