Ischemic stroke detection was carried out using a combination of Machine Learning and Deep Learning techniques, supported by a custom-built Graphical User Interface (GUI). A dataset containing categorized images of 'Ischemic' and 'Normal' cases was used. After loading the dataset, feature extraction and preprocessing steps were performed, followed by splitting the data into training and testing sets. The Support Vector Machine (SVM) algorithm achieved an accuracy of 85%, whereas the Convolutional Neural Network (CNN) achieved a significantly higher accuracy of 98%. Comparative analysis revealed the superior performance of CNN over SVM in stroke image classification. The trained CNN model was further used for predicting new test images, successfully distinguishing between Ischemic and Normal cases. These results highlight the effectiveness of deep learning approaches for accurate ischemic stroke detection from medical images
Thrisha et al. (Thu,) studied this question.