Transfer Learning Methods for Classification of COVID-19 Chest X-ray Images

An important point-of-care diagnostic technology for COVID-19 is x-ray imaging of the lungs. Here we present a novel deep learning training method which combines both supervised and reinforcement learning methodologies which allows transfer learning in a convolutional neural network (CNN). The method integrated hill-climbing techniques and stochastic gradient descent with momentum to train the CNN architectures without overfitting on small datasets. The model was trained using the Kaggle COVID-19 Chest Radiography dataset. The dataset consists of 219 COVID-19 positive images, 1341 normal images, and 1345 viral pneumonia images. Since training of a CNN can be affected by bias and depends on the limitations of available computing power, the data set was reduced to 219 images for each class. From each of the classes, 150 random images were used for training the CNN algorithm and the model was tested with 69 independent images. Transfer training was done on three models, namely, VGG-19, DenseNet-201, and NASNet. The DenseNet-201 architecture performed the best in terms of accuracy achieving an accuracy of 96.1%. The VGG-19 and DenseNet-201 had sensitivity of 91.3 % while NASnet had a slightly higher sensitivity of 92.8%. This shows that we can have high confidence of the classification results achieved by these models. These results show that deep learning methodologies can be used for identifying COVID-19 patients quickly and accurately.