• Akshaya M D
• Farhan N
• Sreelakshmi S P
• Anandhu Uday
• Mithun Vijayan

Public health burden of stroke is staggering throughout the world. Stroke is a medical condition in which poor blood flow to the brain causes cell death. Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) are the two frequently used modalities for brain imaging. Fast and accurate treatment is a necessity. Conventionaly, medical images are analysed manually for stroke detection. The development of automated systems can improve medical outcomes. Convolutional Neural Networks (CNN) have been shown to have excellent performance in automating multiple image classification and detection tasks. The proposed CNN architecture has 13 layers. In this paper we used 2000 images to train and test the CNN model. The model had obtained classification accuracy of above 90%. Thus the model has the capability to assist doctors in making preliminary diagnosis

Brain stroke detection, image preprocessing, convolutional neural networks

"Brain stroke detection using convolutional neural networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 10, page no.e304-e307, October-2021, Available :http://www.jetir.org/papers/JETIR2110457.pdf

"Brain stroke detection using convolutional neural networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 10, page no. ppe304-e307, October-2021, Available at : http://www.jetir.org/papers/JETIR2110457.pdf