Small-Cell Lung Cancer Detection Using a Supervised Machine Learning Algorithm

Abstract

Cancer-related medical expenses and labor loss cost annually $10,000 billion worldwide. Lung cancer-related deaths exceed 70,000 cases globally every year. Furthermore, 225,000 new cases were detected in the United States in 2016, and 4.3 million new cases in China in 2015. Statistically, most lung cancer related deaths were due to late stage detection. Like other types of cancer, early detection of lung cancer could be the best strategy to save lives. In this paper, we propose a novel neural-network based algorithm, which we refer to as entropy degradation method (EDM), to detect small cell lung cancer (SCLC) from computed tomography (CT) images. This research could facilitate early detection of lung cancers. The training data and testing data are high-resolution lung CT scans provided by the National Cancer Institute. We selected 12 lung CT scans from the library, 6 of which are for healthy lungs, and the remaining 6 are scans from patients with SCLC. We randomly take 5 scans from each group to train our model, and used the remaining two scans to test. Our algorithms achieves an accuracy of 77.8%.