Deep Neural Networks for Brain Tumor Image Segmentation and Detection

Medical image analysis is a challenging and complex field these days. This discipline focuses especially on the processing of MRI (Magnetic Resonance Imaging) images. It offers multiple methods for locating brain tumors in MRI brain images and compares the precision of all the findings. Convolutional neural networks (CNN) and ResNet architectures are used to train the model. As deep learning models are highly efficient and correctly identify whether the MRI picture of a tumor is healthy or unhealthy. In this work, high-level features are extracted from the input images using the CNN architecture, which has multiple pooling layers. To create the final classification model, fully connected layers are then routed through the extracted characteristics. However, CNN has some drawbacks, and to overcome these issues, a ResNet based architecture has been used. Additionally, U-Net-based MRI brain tumor segmentation algorithms have gained popularity because they significantly improve segmentation accuracy by infusing high-level and low-level feature information via skip connections. The suitability of an attention module called Attention Gate, which was recently developed, for tasks involving the segmentation of brain tumors has also been explored in this work.