Abstract
Ischemic stroke remains a leading cause of death and disability. Accurate segmentation of affected areas on brain CT scans plays a crucial role in timely diagnosis and treatment decisions. This study examines an ensemble approach to ischemic stroke foci segmentation on non-contrast CT scans using three 3D U-Net models. CT scans of 50 patients with confirmed acute ischemic stroke (provided by the International Tomography Center, SB RAS) were used as input data. Experiments demonstrated that the 3D U-Net ensemble outperforms each of the individual models in segmentation quality, achieving a Dice coefficient of 0.7008. Analysis of the results demonstrates more accurate delineation of pathological areas and a reduction in segmentation errors. The proposed approach can find application in automated diagnosis of stroke and other diseases requiring accurate segmentation of medical images.