Using image processing and deep learning for automatic brain tumor detection in MRI images

Automatic brain tumor detection from MRI images using image processing and deep learning is one of the prominent challenges in medical sciences. This research focuses on analyzing and comparing various deep learning models for brain tumor detection, with an emphasis on the impact of preprocessing, image size, and model architectures. Results obtained from the BRATS ۲۰۲۰ and BraTS ۲۰۲۱ datasets demonstrated that DenseNet-۱۲۱ and ResNet-۵۰ models outperformed simpler models like VGGNet-۱۶ in terms of accuracy. In particular, the DenseNet-۱۲۱ model achieved the best performance with an accuracy of ۹۴.۳% in identifying different types of brain tumors (glioma, astrocytoma, and meningioma), while the ResNet-۵۰ model, with an accuracy of ۹۱.۲%, ranked second. Preprocessing results showed that noise reduction with Gaussian filters, signal intensity normalization, and data augmentation had a significant impact on improving model accuracy. Specifically, data augmentation improved model accuracy by ۸% and helped prevent overfitting. T۲-weighted MRI images had the highest accuracy of ۹۲.۱%, while T۱-weighted MRI images showed an accuracy of only ۸۶.۵%. Compared to traditional methods such as manual thresholding, deep learning models demonstrated significantly better performance. For example, the DenseNet-۱۲۱ model achieved an accuracy of ۹۴.۳% in detecting brain tumors, compared to ۷۵.۲% accuracy with traditional methods. This difference highlights the ability of deep learning models to learn complex and nonlinear features from MRI images. Additionally, model interpretability analysis using techniques like Grad-CAM and LIME showed that these models could more transparently identify tumor-related regions and provide more understandable decisions for doctors. This feature helps clinicians utilize the model's results more confidently in clinical processes. Ultimately, the results of this study suggest that the use of complex deep learning models, combined with precise preprocessing and optimal data selection, can serve as reliable tools for automatic brain tumor detection.

کلیدواژه ها:

Image processing ، deep learning ، brain tumor detection ، MRI images ، DenseNet-۱۲۱ ، ResNet-۵۰ ، image preprocessing ، glioma ، astrocytoma