Ischemic and hemorrhage stroke prediction using DL algorithm

For the last few decades, machine learning is used to analyze medical dataset. Recently, deep learning technology gaining success in many domains including computer vision, image recognition, natural language processing and especially in medical field of radiology. This project attempts to diagnose brain stroke from CT using CNN and deep learning models. The proposed methodology is to classify brain stroke CT images into normal and abnormal images. In particular, three types of convolutional neural network that are ResNet, MobileNet and VGG16 are used. For classification, we passed pre-processed stroke CT for training, trained all layers and classify normal and abnormal patient. Then this abnormal patient data stored into two-dimensional array and passed this to get result. The experimental result show that classification model achieves best accuracy. Through experimental results, we found that deep learning models not only used in non-medical images but also give accurate result on medical image diagnosis, especially in brain stroke detection.

 Keywords: Brain stroke, deep learning, convolutional neural network.