Digital Twins for Brain Tumor Detection using MRI Images by Deep Learning

The aberrant growth and proliferation of brain tumors causes them to have one of the highest fatality rates among all cancers, despite the rarity of the disease. When aberrant muscles buildup in the brain, a tumor forms. There is a wide variety of aberrant tissue types, but most of the time they grow normally and then die off without bothering anyone. There are a few other names for digital twins: digital-mirror, mapping, and duplicate. Each of these words describes the similar thing; they are interchangeable. It is a method for moving data across other domains, whether that data is digital or physical. The goal of image processing is to accomplish some task by adding or removing data from a picture. An example of a neural network is a convolutional neural network, which takes picture signals as input and outputs either the full image or a choice of its modules. This study details a method for diagnosing brain malignancies using magnetic resonance imaging (MRI) scans by employing digital twins and sophisticated machine learning techniques. Using digital devices connected to the IoT, MRI images are stored in a central cloud. After that, we access the cloud storage to get the input images and any other health-related data. Features are selected using the Particle Swarm Optimization method. Image classification of brain tumors is accomplished by means of deep-learning(DL) strategies such as CNN. When it comes to investigating MRI-images for the aim of detecting brain-tumors (BT), the CNN algorithm shows significantly better accuracy.