Systematic mapping review of lung cancer diagnosis based on machine learning

In most nations, lung cancer (LC) is the main cause to mortality cases occurring due to tumors to males and females. Lung nodules (masses) are recognized through digital technologies support precise diagnosis using medical imaging techniques such as CT-scan, X-rays and MRI. As the nodules are normally connected to the blood vessels, identification of lung nodules is a difficult task. Several studies illustrate that diagnosing or detecting such cases earlier is regarded the best successful method to counter this disease. Many systems have been developed that automatically identify lung tumors by using magnetic resonance spectroscopy and pattern recognition methods. Despite the encouraging consistency of the classification, none of these schemes have set their course in clinical practice, which also concerns the lack of clarity concerning the process of taking decisions. In this paper, we present a systematic mapping study on lung tumors recognition. After four sorting methods, we obtained 375 relevant studies in total. After applying four filters manually, 48 papers as primary studies related to the main topic are selected as listed in Appendix (A). The selected papers classified them with respect to several facets. The results provide an overview of the existing relevant studies in reported in the literature, highlight focus areas and research gaps.