It is essential to classify brain tumors from magnetic resonance imaging (MRI) accurately for better and timely treatment of the patients. In this paper, we propose a hybrid model, using VGG along with Nonlinear-SVM (Soft and Hard) to classify the brain tumors: glioma and pituitary and tumorous and non-tumorous. The VGG-SVM model is trained for two different datasets of two classes; thus, we perform binary classification. The VGG models are trained via the PyTorch python library to obtain the highest testing accuracy of tumor classification. The method is threefold, in the first step, we normalize and resize the images, and the second step consists of feature extraction through variants of the VGG model. The third step classified brain tumors using non-linear SVM (soft and hard). We have obtained 98.18% accuracy for the first dataset and 99.78% for the second dataset using VGG19. The classification accuracies for non-linear SVM are 95.50% and 97.98% with linear and rbf kernel and 97.95% for soft SVM with RBF kernel with D1, and 96.75% and 98.60% with linear and RBF kernel and 98.38% for soft SVM with RBF kernel with D2. Results indicate that the hybrid VGG-SVM model, especially VGG 19 with SVM, is able to outperform existing techniques and achieve high accuracy.
翻译:从磁共振成像(MRI)对脑肿瘤进行准确分类,以便更好、及时地治疗病人。 在本文中,我们提出一种混合模型,使用VGG和Nonlinear-SVM(软硬)一起使用VGG和Nonlinear-SVM(软和硬)对脑肿瘤进行分类:显微镜和显性、肿瘤和非触动性。VGG-SVM模型为两个等级的两个不同的数据集进行了培训;因此,我们进行了二进级分类。VGG模型通过PyToch Python图书馆培训,以获得肿瘤分类的最高精确度。在第一阶段,我们建议采用三重混合模型,使用VGG和SVM(软和硬)对图像进行标准化和调整,通过VGFM模型进行特征提取。