CAD Based Brain Tumor Detection Using Enhanced Net Algorithm

Abstract

This paper aims to compare the performance of a deep learning-based approach for brain tumor detection in magnetic resonance images (MRI) with a support vector machine (SVM) algorithm. The deep learning approach is based on transfer learning with the EfficientNet-B0 model and uses several preprocessing steps, including skull stripping, intensity normalization, and erosion and dilation, to enhance the tumor regions in the MRI images. The SVM algorithm uses a combination of texture and intensity features to classify the MRI images as tumor or non- tumor. The deep learning approach achieved a higher accuracy of 96.41% compared to the SVM algorithm, which achieved an accuracy of 92.81%. The deep learning approach also showed better performance in terms of sensitivity, specificity, and F1-score. The results of the study suggest that the deep learning-based approach is more effective than the SVM algorithm for brain tumor detection in MRI images. The proposed approach could potentially improve the accuracy and efficiency of clinical diagnosis of brain tumors, leading to better patient out- comes.