A Dynamic Optimization and Deep Learning Technique for Detection of Lung Cancer in CT Images and Data Access Through Internet of Things

Now-a-days the most common pretentious disease is the lung cancer, which has become more prevalent in the world that primarily infects the pulmonary nodules of the lungs. At present the most propitious way to increase survival rate in cancer patients is by early detection. Commonly the lung cancer is diagnosed by radiologists with an inclusive analysis of CT images, which proceeds comprehensively a longer time. The analysis of lung cancer in imaging modalities like CT images is crucial. Image processing itself act as a progressive diagnostic tool for analysis of medical imaging modalities. The existing procedures for detection of lung cancer like PSO with morphological yields poor accuracy. In this work the novelty is established by considering cuckoo-search optimization algorithm along with ostu threshold for segmentation, CNN as classifier and LBP as feature extraction procedure on CT images for detection of lung cancer. In addition, IoT technology is carried out using raspberry PI processor to establish a network to share the details among the medical professionals to exchange opinions for final treatment. Finally, various parameters were calculated and compared with existing procedures especially accuracy is around 98% and MSE within 1.5 is obtained. Thus, the proposed method gives an optimal solution on comparison with respect to all the parameters.