RETRACTED CHAPTER: Automatic Detection of Coagulation of Blood in Brain Using Deep Learning Approach

There are many medical diagnostic applications where automated flaw identification in medical imaging is a promising new topic. Automatic tumour diagnosis using magnetic resonance imaging (MRI) provides crucial data for therapeutic decision making. When looking for errors in brain MRIs, the human evaluation is the gold standard. This strategy is impossible due to the enormous quantity of data being handled. For this reason, robust and automated classification methods are essential for lowering death rates. Therefore, reliable and automated categorization systems are crucial for reducing human mortality. Since saving the radiologist's time and achieving proven accuracy is a priority, automated tumor detection systems are being developed. Due to the complexity and diversity of brain tumors, detecting them using MRI is challenging. To address the limitations of previous approaches to tumor detection in brain MRI, we suggest using Deep Learning InceptionV3, VGG19, ResNet50, and MobileNetV2 transfer learning. Utilizing a deep learning framework and an image classifier, brain cancer may be detected via MRI with remarkable accuracy. We also use the flask framework to predict the presence of tumors in web applications.