An efficient Algorithm for medical image classification using Deep Convolutional Network: Case of Cancer Pathology

Automatic classification of medical images especially of tissue images is an important task in computer aided diagnosis (CAD) systems. Deep learning methods such as convolutional networks (ConvNets) outperform other state of-the-art methods in images classification tasks. This article describes an accurate and efficient algorithms for this challenging problem, and aims to present different convolutional neural networks to classify the tissue images. first, we built a model that consist of feature extraction and the classification with simple CNN, the second model consist of a CNN as feature extractor by removing the classification layers and using the activations of the last fully connected layer to train Random Forest, and the last one using transfer learning --Fine-Tuning-- pre-trained CNN "DenseNet201". Finally, we have evaluated our models using three metrics: accuracy, Precision and F1 Score.