Tumor Categorization Model (TCM) using Soft Computing Techniques for Providing Efficient Medical Support in Brain Tumor Treatments

Abstract

In Medical Image Processing, brain tumor detection and segmentation is a time consuming and tedious process, which is most significant for providing appropriate treatment and increase the survival rate of patients. With the advancements available in medical fields, soft computing techniques are incorporated to accurate detection and classification of brain tumors. In addition to brain tumor detection, it is important to categorize the tumor stage based on their features. For that concern, this paper develops a Tumor Categorization Model (TCM) that includes image processing and soft computing techniques. Here, pre-processing is carried out using modified Gabor filter and segmentation process is performed with OTSU thresholding. Following segmentation, region growing is processed based on the pixel intensities of input MRI brain images. Further, Discrete Wavelet Transform is enforced for extracting image features and gray-level co-occurence matrix features are also derived for appropriate classifications. Finally, the input MRI images are classified using Boosting Support Vector Machine (BSVM) with the benchmark dataset called DICOM and BraTS dataset. The experimental results demonstrate accurate brain tumor detection and categorization by the efficient incorporation of image processing and soft computing methodologies, provides efficient clinical support in providing treatments.