Brain Hemorrhage Diagnosis by Using Deep Learning

We propose an approach to diagnosing brain hemorrhage by using deep learning. In particular, three types of convolutional neural networks that are LeNet, GoogLeNet, and Inception-ResNet are employed. In the training phase, we only train the last fully-connected layers of GoogLeNet and Inception-ResNet, but do train all layers of LeNet. We build a dataset consisting of 100 cases collected from the 115 Hospital, Ho Chi Minh City, Vietnam. The experimental results show that LeNet, GoogLeNet, and Inception-ResNet achieve accuracy of 0.997, 0.982, and 0.992 respectively on the dataset. Through experimental results, we found that convolutional neural networks are pre-trained with non-medical images like GoogLeNet or Inception-ResNet can be used in medical image diagnosis, particularly in brain hemorrhage diagnosis. And, we confirm that among the three deep models, LeNet is the most time-consuming model.