Automatic Lung Cancer Prediction from Chest X-ray Images Using the Deep Learning Approach

Abstract

Since, cancer is curable when diagnosed at an early stage, lung cancer screening plays an important role in preventive care. Although both low dose computed tomography (LDCT) and computed tomography (CT) scans provide greater medical information than normal chest x-rays, access to these technologies in rural areas is very limited. There is a recent trend toward using computer-aided diagnosis (CADx) to assist in the screening and diagnosis of cancer from biomedical images. In this study, the 121-layer convolutional neural network, also known as DenseNet-121 by G. Huang et. al., along with the transfer learning scheme is explored as a means of classifying lung cancer using chest x-ray images. The model was trained on a lung nodule dataset before training on the lung cancer dataset to alleviate the problem of using a small dataset. The proposed model yields 74.43±6.01% of mean accuracy, 74.96±9.85% of mean specificity, and 74.68±15.33% of mean sensitivity. The proposed model also provides a heatmap for identifying the location of the lung nodule. These findings are promising for further development of chest x-ray-based lung cancer diagnosis using the deep learning approach. Moreover, they solve the problem of a small dataset.