BHCNet: Neural Network-Based Brain Hemorrhage Classification Using Head CT Scan

Brain Hemorrhage is the eruption of brain arteries due to high blood pressure or clotting that could be a cause traumatic injury death. It medical emergency in which doctor also need years experience immediately diagnose region internal bleeding before starting treatment. In this study, deep learning models Convolutional Neural Network (CNN), hybrid CNN + LSTM and GRU are proposed for classification. The 200 head CT scan images dataset used boost accuracy rate computational power models. major aim study use abstraction on set fewer because most crucial cases extensive datasets not available spot. image augmentation imbalancing methods adopted with model design unique architecture named as Classification based (BHCNet). performance approach analyzed terms accuracy, precision, sensitivity, specificity F1-score. Further, experimental results evaluated by comparative analyses balanced imbalanced CNN, promising achieved gain highest outperforms reveals effectiveness accurate prediction save life patient meantime fast employment real scenario.