Artificial Intelligence Enabled Framework for Automatic Brain Stroke Detection

Brain stroke is causing severe damage to health besides causingdeaths across the globe. Healthcare industry has got technological innovations to improve quality of service. With the emergence of Artificial Intelligence (AI) medical image analysis has unprecedented possibilities. Deep learning approaches have gained popularity for analysing medical images for automatic diagnosis. Convolutional Neural Network (CNN) based deep learning models such as VGG16, ResNet50 and DenseNet121 are found to be suitable for image processing. However, as one size does not fit all, there is need for optimizing these models in order to adapt them for brain stroke detection and leverage their performance. Towards this end, in this paper, we proposed an AI enabled framework with optimizations to the aforementioned deep models. Towards this end we proposed an algorithm known as Intelligent Learning for Stroke Detection (ILSD). The optimized models are found to have increased prediction performance. Enhanced DenseNet121 showed highest accuracy with 99.82%.