Convolutional Neural Networks Architecture for Processing Brain MRI Images

The review of existing solutions in the form of algorithms and ready-made models of neural networks for processing brain images is carried out. The features and differences between the requirements for models and their architectures that process images for non-medical purposes and models trained to work with medical data are analyzed. Work was planned to develop an architecture for working with a small amount of marked-up data for training the model. as well as the preparation of the necessary dataset.