ABSTRACT Lung cancer is a primary origin of cancer‐based mortality. In the early phases, the recognition of pulmonary cancer can greatly enhance the rate of survival. The manual delineation of lung nodules by medical experts is a tiresome operation. In previous years, the high growth of cloud computing has revolutionized the medical sector to another level. Since lung cancer's causes stay unclear, the prevention process becomes relatively impossible, hence the lung tumor's timely identification is the primary and only way to treat lung cancer. Nowadays, in developed countries, this situation is highly enhanced by employing conventional data sources about lung cancer. Nevertheless, because of the poor data collection approach's synchronization, the gathered data is heterogeneous, and immediately cannot be employed. Therefore, in this developed framework, the cloud‐based paradigm for detecting lung cancer disorder utilizing the adaptive deep learning technique is introduced. First, the structural representation of cloud computing is explained and used in the medical application. Further, the necessary images are gathered from the standard data sources. In order to diagnose lung cancer, the novel model is designed and named as Adaptive Hybrid Residual Attention Network (AHRANet), in which the “Convolutional Neural Network” (CNN) is associated with the Densenet. For improving the efficiency, the Random‐integer Revamped Hippopotamus Optimization (RRHO) is recommended for optimizing the parameters present in the model. Finally, the efficacy of the system is validated with multiple metrics. In contrast with other techniques, the designed system provides promising results to evince a superior diagnosis of lung cancer ailments.
Medida et al. (Sun,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: