Effective Brain Stroke Prediction with Deep Learning Model by Incorporating YOLO_5 and SSD

Abstract

Ischemic stroke is a life-threatening disorder that significantly reduces a person's lifespan. The timely diagnosis of stroke heavily relies on medical imaging techniques such as magnetic resonance imaging (MRI), computerized tomography (CT), and x-ray imaging. However, the manual localization and analysis of these images can be time-consuming and yield less accurate results. To address this challenge, we propose the implementation of deep-learning object detection techniques for computerized lesion identification in medical images. In this study, we employ three categories of deep learning object identification networks: deep convolutional neural network (DCNN), you only look once (YOLO) 5, and single-shot detector (SSD). By leveraging these advanced deep learning models, we aim to reduce the effort and time required for screening and analyzing a significant number of daily medical images, including MRI, CT, and x-ray images. With the addition of YOLO5 and SSD among these networks, the accuracy achieved was 96.43%, demonstrating their effectiveness in accurately identifying lesions associated with ischemic stroke