A cloud-based deep learning model in heterogeneous data integration system for lung cancer detection in medical industry 4.0

Currently, lung cancer has become one of the most common and deadliest types of cancer. Due to its severity, many countries are now encouraging their at-risk citizens to test and treat lung cancer early. Lung cancer has been worse for poor regions or countries, whose citizens are more susceptible to lung cancer, as the local medical resources and healthcare provider level are inadequate. In recent years, this situation can be significantly improved by leveraging the existing datasets about lung cancer in developed countries. However, due to the poor synchronization of data collection methods, the collected data is heterogeneous, and can't be readily used. Artificial intelligence (AI), big data, cloud computing, and the internet of things accelerate the 4th revolution in the medical industry, and we called it medical industry 4.0. In the medical industry 4.0, lung cancer can be early detected by using a very intelligent approach. In this paper, using AI and cloud platform techniques in the medical industry 4.0, we propose an intelligent detection system including data integration, detection, historical cases comparison, similar cases inquiry, and retrieval for lung cancer. In this system, doctors can integrate the heterogeneous data at hand, and source a large amount of integrated data as a reference when treating the patient. A cloud-based deep learning model is integrated into this system, and then a content-based image retrieval system for similarity comparison is used. Finally, some public datasets are used to train and test this system, and results prove its performance is better than that of some baseline approaches. Then the similar case finding is evaluated with cosine similarity and all similarities reach over 0.93. The heterogeneous data integration system creates a good effect in helping doctors and patients access better diagnosis and treatment for lung cancer.