Cerebral infarction is a leading cause of mortality worldwide, resulting from the blockage of an artery that restricts blood flow and oxygen to brain tissues. Computed Tomography (CT) is a widely used imaging tool for early stroke assessment. This study proposes an automated detection model for cerebral infarction in CT brain images using a 3D U-Net model based on Convolutional Neural Networks (CNN). To improve and segment the impacted brain tissues, the system uses preprocessing techniques such slice selection, picture averaging, band-pass filtering, and variation model decomposition. The Medical Image Segmentation framework with CNN (MIS CNN) is used for efficient and accurate detection. The proposed model enhances diagnosis accuracy, assists radiologists in early stroke identification, and contributes to reducing the mortality rate by enabling timely medical intervention.