Brain Tumor Classification Based on Fuzzy Method and Optimized Transfer Learning

Abstract

Correct diagnosis of the type of brain tumor plays an important role in diagnosis and treatment decisions. Machine learning techniques are very useful for classifying tumors with deep features without manual intervention. Development in deep learning and learning transfer using deep convolution neural networks (CNN) has made great strides. In this study, deep transfer learning method has been used to extract deep features without hand intervention and to detect different types of tumors using fuzzy method method.Transfer learning is a way of transferring information during training and testing. In this study, extract of deep features from image using CNN were used to diagnose tumors. Here, fuzzy meThod classifier is used for diagnosis and the accuracy of tumor diagnosis is 99.9%. The results show that the proposed method has a high accuracy for diagnosing different types of tumors.Based on the obtained results, it can be concluded that the proposed method is an effective and reliable approach for detecting brain tumors.