Brain tumour segmentation is a significant task in the Medical Image Processing (MIP). Early diagnosis of the brain tumours plays an important role in improving treatment possibilities and maximizes the survival rate of the patients. Manual segmentation of the brain tumours for the cancer diagnosis form large amount of MRI images that generated in clinical routine, its complex and time consuming task. So, the automatic brain tumour image segmentation process is required. In this research, a tumour portion is segmented from the brain image by using Adaptively Regularized Kernel-Based Fuzzy C-Means (ARKFCM) algorithm. The input images are resized like 256×256 in the pre -processing stage. The pre-processed MRI image segmented by ARKFCM, which is a flexible high-level Machine Learning (ML) technique to locate the object in a complex template. Next, Hybrid Feature Extraction (HFE) performed on the segmented image to improve the feature subsets. The feature selection process was performed by Kernel Nearest Neighbour (KNN) based Genetic Algorithm (GA) in order to acquire the best feature values. The best feature values given to the Deep Neural Network (DNN) classifier as an input, which is classified into Meningioma, Glioma and Pituitary regions in the MRI images. The performance of proposed ARKFCM -HFE -DNN method is validated by T1-WCEMRI dataset. The experimental outcome showed that the ARKFCM -HFE -DNN method improved the average classification accuracy up to 6.19 % than existing classification techniques such as Convolution Neural Network (CNN) and Support Vector Machine (SVM).

No abstract

In this research work, a new automated system is developed for brain tumor detection by using Magnetic Resonance Imaging (MRI) on the basis of machine learning techniques. The major concerns in the brain tumor detection are time consuming, and the classification accuracy dependsonly on clinician’s experience. To address these issues, a new supervised system is developed for brain tumor detection. In this research study, a new segmentation approach was used for improving the brain tumor detection performance and to diminish the complexity of the system. Initially, Anisotropic Diffusion Filter (ADF) was used as an image pre-processing technique for removing noise from the collected brain image. Then, Berkeley Wavelet Transformation (BWT) was utilized for converting the spatial form of pre-processed MRI image into temporal domain frequency. Besides, Support Vector Machine (SVM) was usedas a classification technique to classify the normal and abnormal regions. SVM classifier effectively diminishes the size of resulting dual issue by developing a relaxed classification error bound. In addition, the undertaken classification approach quickly speed up the training process by maintaining a competitive classification accuracy. From the experimental analysis, the proposed system improved dice coefficient >0.9 compared to the existing systems. The experimental investigation validated and evaluated that the proposed system showed good performance related to the existing systems in light of dice coefficient and accuracy.