Adaptive Lung Diseases Images Classification Technique Based on Deep Learning

Medical images have made an important contribution to improving the accuracy and effectiveness of disease diagnosis, such as diseases related to lung, heart, liver, kidney, etc. Pneumonia has increased rapidly in the world in recent years. Chest X-ray image analysis is a common method for detecting lung diseases. An advanced artificial intelligence system will help doctors have accurate conclusions, timely treatment for patients and reducing mortality. Using machine learning on X-ray images is of great interest, but research results are still limited in accuracy. This paper proposed an adaptive technique for lung diseases image classification based on the deep learning method. We improved the convolutional neural network for lung diseases image classification, created a training model with a suitable number of hidden network layers and optimal algorithms to detect pneumonia images. As a result, the rate of correct detection of pneumonia image was 98.72%. We used chest X-ray images dataset that published by Kaggle, including 5863 chest X-ray images. The results of the proposed method are better than the other methods.