Medical image processing using deep convolutional neural networks

The field of medical image processing includes a wide range of applications from automated screening of diabetic retinopathy based on retinal images to MRI segmentation for tumor recognition. Various machine learning classification and clustering approaches have been studied in literature with the purpose of improving the accuracy of the screening methods. Some studies used manually feature extraction of fundus images by image processing experts. In recent years, a new approach for image classification and diagnosis without using any manual feature extraction is proposed based on convolutional neural network (CNN). The CNNs are based on deep learning concept have more convolutional and hidden layers and are more powerful envolving the high dimension inputs such as medical images. In medical imaging and diagnosis, training a deep CNN from scratch is difficult because it requires a large amount of labeled training data and the training procedure is a time consuming task to ensure proper convergence. Therefore, a very common method to train CNNs for medical diagnosis is fine-tuning a pre-trained CNN. Some of these powerful pre-trained CNNs are the GoogleNet, CifarNet and AlexNet which have been trained on the ImageNet as a a large databas