Detecting brain tumor using deep learning approaches

This master's thesis examines the use of deep learning methods for the detection of brain tumors. Brain tumors, though relatively rare worldwide, are serious malignancies with high mortality rates. Early diagnosis and accurate classification are crucial in the treatment process. This study evaluates the performance of deep learning methods, particularly convolutional neural networks (CNNs), in detecting and classifying brain tumors. The aim is to detect brain tumors from MRI and CT images using various deep learning models and machine learning algorithms. In this study, deep learning models such as VGG19, Inception V3, and MobileNet, along with machine learning algorithms like K-Nearest Neighbors (K-NN ) and Support Vector Machines (SVM), were utilized. Model performances were evaluated using metrics such as accuracy, precision, recall, F1 score, and ROC-AUC. The results indicate that deep learning models offer high accuracy and reliability in detecting brain tumors. Notably, the VGG19 model demonstrated superior performance compared to other models. These findings suggest that deep learning methods can be an effective tool in medical image analysis and have potential applicability in clinical practice. Future studies may focus on improving performance by using larger datasets and different deep learning models.