Diagnosis of lung cancer in Artificial Intelligence age: A systematic review

Background and aims: Nearly one-quarter of all cancer deaths worldwide are due to lung cancer,making this disease the leading cause of cancer death among both men and women. The key issuein the fight against lung cancer is the detection and diagnosis of this disease at an early stage. Artificialintelligence has been proposed as promising tool to help this purpose. The main objectiveof this study was to review artificial intelligence techniques and their effectiveness in diagnosisof lung cancer.Method: A comprehensive search was performed in PubMed, Scopus, ISI Web of Science, Embase,and Cochrane databases from ۲۰۱۷ to February ۲۰۲۳ in order to identify the studies thatused artificial intelligence to diagnose lung cancer and based on the relevancy and details, articleswere selected from all the currently available literature.Results: The systematic review identified ۲۵ eligible studies, of which ۱۸ used radiomics modelsand application of deep learning in diagnosis of lung cancer by computed tomography (CT) scan,low-dose CT (LDCT) scan and chest X-ray images like [۱۸F]FDG-PET/CT and artificial intelligencefilm reading system. Meanwhile, ۷ studies were based on molecular analysis, using decisiontree methods, neural networks and support vector machines (SVM) for prognosis predictionin lung cancer.Conclusion: With the advance of technology, artificial intelligence could have great potentialimpacts in lung cancer diagnosis. In doing so, artificial intelligence can help in the early detectionof cancer and provide appropriate therapy through the available information. Although artificialintelligence is an invaluable tool there are some challenges about its widespread implementationand availability. For instance artificial intelligence relies heavily on data, and data acquisitioncontinue to be a challenge that artificial intelligence will need to overcome. Furthermore, patientand provider trust and Privacy concerns are other obstacles. Artificial intelligence combined withradiography, genomics, surgery, clinical oncology, pathology, electronic health records, and otherdata streams gathered into a powerful comprehensive diagnosis system and combined with ۵Gmay be of great therapeutic value in lung cancer.