Remote Pulmonary Nodule Detection Based on 6G Network Information System and 3D Visual Transformation

Slight growth in the lung that can be either round or oval is called a pulmonary nodule. Imaging examinations, such as CT scans or chest X-rays, performed for other reasons often discover these nodules as an incidental observation. Remote pulmonary nodule diagnosis is a major obstacle in healthcare, particularly in areas without quick access to specialist medical knowledge. The objective of this study was to use 3D visual transformation and 6G network information system-based remote pulmonary nodule detection. First, we examine the 800 low-dose lung CT images collected from the TIANCHI17 dataset, made available for the initial round of the Aliyun Tianchi big data contest in early 2017. We used Histogram Equalization for preprocessing, improving local contrast and structure visualization. K-means clustering for segmentation is utilized. Lung structures are segmented with distinct values by clustering pixels based on tissue type. We proposed the modified Gaussian advanced Dwarf mongoose optimised Convolutional neural networks (MGADMO-CNN) spontaneously train data that capture layered representations of image information during training. Finally, the remaining data is used to test the 6G network model's performance. The results showed that the proposed perform to compare the existing methods. This allows an assessment of the average value, accuracy, precision-recall analysis, loss function, and AUC-ROC of the suggested approach. Therefore, our suggested method for assessing Remote Pulmonary Nodule Detection will enhance 3D Visualization and 6G Network Information System data.