Segmentation of brain regions affected by ischemic stroke helps to overcome the main obstacles in modern studies of stroke visualization. Unfortunately, contemporary methods of solving this problem using artificial intelligence methods are not optimal. Therefore, in the study we consider how to increase the efficiency of segmentation of the stroke focus using computer perfusion imaging using modifications based on UNet. The network was trained and tested using the ISLES 2018 dataset. The publication includes an analysis of the results obtained, as well as recommendations for future research. By choosing the appropriate model parameters, our approach can be easily applied to detect ischemic stroke. We present modified U-Net models with two ResNet blocks as U-Net+ ResNetblock 1 and U-Net +ResNetblock 2, as well as a modified UNet model.  Due to the small number of images for training the model, the best results were obtained by applying data preprocessing and object representation approaches, as well as data normalization methods to avoid overfitting. The results show that the modified UNet model is superior to other models in terms of average distance and recall, that are significant parameters for segmentation of the stroke.

In the field of stroke imaging, deep learning (DL) has enormous untapped potential. When clinically significant symptoms of a cerebral stroke are detected, it is crucial to make an urgent diagnosis using available imaging techniques such as computed tomography (CT) scans. The purpose of this work is to classify brain CT images as normal, surviving ischemia or cerebral hemorrhage based on the convolutional neural network (CNN) model. In this study, we propose a computer-aided diagnostic system (CAD) for categorizing cerebral strokes using computed tomography images. Horizontal flip data magnification techniques were used to obtain more accurate categorization. Image Data Generator to magnify the image in real time and apply any random transformations to each training image. An early stopping method to avoid overtraining. As a result, the proposed methods improved several estimation parameters such as accuracy and recall, compared to other machine learning methods. A python web application was created to demonstrate the results of CNN model classification using cloud development techniques. In our case, the model correctly identified the drawing class as normal with 79% accuracy. Based on the collected results, it was determined that the presented automated diagnostic system could be used to assist medical professionals in detecting and classifying brain strokes.