• Pavankumar Shirol
• Abahy Itagi
• Shashidhar Chavan
• Vijay Yaragatti

Brain hemorrhage is the severe disease occurs when the arteries in the brain burst due to high blood pressure or blood clots, which can lead to severe injury or death this type of medical emergency, a doctor must have years of experience in order to identify the site of internal bleeding quickly enough to begin treatment. In this study, the deep learning models such as Convolutional Neural Network (CNN), hybrid model of U-Net autoencoder, Transfer learning VGG19 are proposed for the Brain Hemorrhage classification. The 368 head MRI scan images dataset is used to boost the accuracy rate and computational power of the deep learning models. The primary goal of this work is comparative analyses of the proposed models that are used to evaluate the experimental results to a smaller set of images, as large datasets are frequently unavailable quickly. The outcome demonstrates the class of the hemorrhage and efficiency of the suggested model in terms of prediction to preserve the patient's life in the short term and quick treatment in practical situations.

Brain Hemorrhage, Deep Learning, Convolution Neural Network, U-Net, MRI

"BRAIN HEMORRHAGE CLASSIFICATION USING DEEP LEARNING TECHNIQUES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.k742-k749, April-2024, Available :http://www.jetir.org/papers/JETIR2404A98.pdf

"BRAIN HEMORRHAGE CLASSIFICATION USING DEEP LEARNING TECHNIQUES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppk742-k749, April-2024, Available at : http://www.jetir.org/papers/JETIR2404A98.pdf