CLASSIFICATION PERFORMANCE COMPARISONS OF DEEP LEARNING MODELS IN PNEUMONIA DIAGNOSIS USING CHEST X-RAY IMAGES

Data set of chest x-ray images of 5840 individuals was classified into two categories which are pneumonia and healthy person using deep learning models: convolutional neural network, convolutional neural network with data augmentation and transfer learning. Loss and classification accuracy values were compared in the classification for three deep learning models. In the comparison of three different deep learning models with two different performance values, 5216 chest x-ray images in the data set were used to train the deep learning models and the remaining 624 were used to test the models.