Deep learning for Intracranial Hemorrhage Detection

A possibly fatal medical condition with a poor prognosis is intracranial hemorrhage (ICH). In previously published work, a more traditional methodology was applied, consisting of multiple stages of alignment, picture analysis, image rectification, manual image segmentation, and classification. For the classification of ICH sub types, we built a convolutional neural network based on the transfer learning model. DenseNet121, Xception, and CNNs were assessed using a broad variety of evaluation criteria to ensure that the model produces excellent results and is accurate. The ultimate output for the identification and classification of ICH subtypes is generated using the Xception model