Segmentation of Acute Ischemic Stroke Lesion from Non-Contrast CT Scans

Abstract This paper proposes an advanced deep learning model for detecting and segmenting the brain acute ischemic lesions from Non-Contrast CT scans. This treatise introduced the 3D CoAtNet model for accurately detecting hypo-intense lesions, which even experienced clinicians fail to detect with satisfactory accuracy. The computer-aided detection and segmentation can act as an assistive tool for clinicians. However, most of the prevalent machine learning models were unable to obtain satisfactory detection accuracy. We propose an efficient deep learning model based on the 3D CoAtNet, which combines the attention mechanism with convolution. It helps the shallow encoder-decoder structure to perform better feature extraction, which plays a crucial role in separating brain tissue and ischemic stroke lesions. Dilation rates of 1, 3, and 5 were applied to each encoder convolution block. We obtained the dice similarity score, which was calculated as 75% and the Jaccard index was 69%.