Detection of lung cancer using deep learning approaches

Cancer is the leading cause of death in every country in the world and the biggest obstacle to increasing life expectancy. According to the World Health Organization's 2019 estimates, cancer ranks first or second among the causes of death over the age of 70 in 112 of 183 countries, and third or fourth in 23 countries. Medical imaging tools are essential in diagnosing early-stage lung cancer and monitoring lung cancer during treatment. Various medical imaging modalities such as chest x-ray, magnetic resonance imaging, positron emission tomography, computed tomography and molecular imaging techniques have been extensively studied for the detection of lung cancer. These techniques have some limitations, including not automatically classifying cancer images, which may make them unsuitable for patients with other pathologies. It is necessary to develop a sensitive and accurate approach for the early diagnosis of lung cancer. Deep learning is one of the fastest growing topics in medical imaging, with rapidly evolving applications covering medical image-based and textural data modalities. With deep learning-based medical imaging tools, clinicians can more accurately and quickly detect and classify lung nodules. This study presents a deep learning-based solution techniques for lung cancer detection and classification.