Detection of Brain Tumor for MRI using Hybrid Method Wavelet and Clustering Algorithm

Abstract

Automatic segmentation of brain tumor using computer analysis aided diagnosis in clinical practice but it is still a challenging task, especially when there are lesions needing to be outlined. In the applications of image-based diagnosis and computer-aided lesion detection, image segmentation is an important procedure .Features extracted from image analysis in companion with image segmentation algorithms are used to provide region-based information for clinical evaluation procedures. Brain tumor diagnosis is easy by using these medical equipments. The physician needs the correct measurement of the tumor area for the further treatment, this need to extract the abnormal part from the 2D MRI scan accurately and measure the region of interest. The HumanComputer interaction is helpful for this procedure. In this search the wavelet transformation is used as well as the Kmean algorithm is used. the wavelet transformation is not sufficient to produce a good result for the brain tumor detection. so the K-mean clustering method with different classes gives best result.

An Automatic Segmentation of Brain Tumor from MRI Scans through Wavelet Transformations

“…Ali et al, proposed the tumor detection method used wavelet transformation and K-means algorithm [5]. The wavelet transformation is not sufficient to produce a good result for the brain tumor detection.…”