Hepatitis is the most serious disease in developing countries. Therefore, early diagnosis is very important to obstacle the effect that can happen as a consequence of this disease. In this case, deep learning can solve the issue at an early stage. An innovative deep learning-based technique to identify hepatitis is presented in this study. In this study 45 layers, convolutional neural network (CNN) architecture connected with three fully connected layers is used in the proposed architecture. The two classes of collected hepatitis datasets are then used to train the suggested CNN model. The model achieved 0.934 classification accuracy. The proposed model was compared to the state of the art at the time. The outcome presented implies that the model's performance is remarkable.
Copyrights © 2023