LAUSR

Tumor classification with MRI (Magnetic Resonance Imaging) is critical, as it consumes an enormous amount of time. Furthermore, this detection method is complicated due to the similarity of both abnormal and normal brain tissues. For earlier treatment planning and clinical assessment of brain tumors, automatic segmentation and classification process using medical images are very challenging. Computerized medical imaging aids clinicians in providing critical therapies to patients while allowing faster decision-making. This work focus on efficient segmentation and classification using machine learning (ML) models motivated by diagnosing tumor growth and treatment processes. To achieve efficient brain tumor detection, different stages in the proposed methodology are pre-processing, segmentation, extraction, selection and classification. Initially, blur-removal is done using NMF (Normalized Median Filter) for image smoothening and quality enhancement. Then segmentation is done using binomial thresholding method. The next step is feature extraction, which is the fusion of GLCM (Gray level co-occurrence matrix), and SGLDM (Spatial Grey Level Dependence Matrix) techniques. Harris hawks optimization (HHO) algorithm is used for feature selection. Finally, KSVM-SSD is used for effective and accurate classification. Here, the brain tumor is classified as benign and malignant using KSVM (Kernel Support Vector Machine) and further classification of the malignant tumor as low, medium, and high using social ski driver (SSD) optimization algorithm. The simulation/implementation tool used here is the PYTHON platform. The performance is analyzed on multiple datasets such as BRATS 2018, 2019 and 2020. Hence, it is proved that the segmentation and classification outcomes are superior compared to existing methods with precision, accuracy, recall, and F1 score. The superiority of the proposed KSVM-SSD model is identified in terms of classification accuracy tested on the BRATS datasets with accuracy as 99.2%, 99.36% and 99.15%, respectively for 2018, 2019 and 2020 BRATS datasets. Higher detection accuracy offers timely and proper diagnosis that can save the lives of people. Hence, these outcomes on tumor detection and classification signifiy improved performance when compared to baseline models.