Lung Tumor Diagnosis Technology Based on 6G Wireless Network Sensors and Big Data Analysis

Big data, gadgets with sensors, and telecommunications technology have all improved the quality of life by enabling more intelligent healthcare services through ubiquitous computing. The use of big data is developed to enhance the healthcare sector. Using software and information and communication technology (ICT), big data connects patients and devices with sensors, medical professionals, and carers. The medical evaluation procedure grows essential in health care as daily generated data grows vast in the 6G-enabled Internet of Medical Things (IoMT). This research proposes a methodology for enhancing the precision of predictions and delivering a real-time diagnosis of illness in the context of 6G-enabled IoMT. This work evaluates lung tumour diagnosis using 6G networks based on big data analysis and deep learning frameworks. In this work, initially, the data is collected through wearable sensors fixed in the patient body. The 6G network is used for faster data transmission and helps monitor patients' health conditions. Next, the collected data is pre-processed by removing noises in the data. The Stationary Wavelet Transform is subsequently employed to extract features. Multispace image reconstruction is utilized to reduce error during image reconstruction, improving lung nodule prediction accuracy. After feature extraction, the arithmetic optimization algorithm (AOA) based on the Hunger Games search (HGS) is used to train the dataset. The controllers of the HGS are utilised in the proposed approach, called AOAHG, to improve the AOA's exploiting capability when assigning the possible area. The created AOAG guarantees an overall improvement in model categorisation by choosing the most pertinent elements. The proposed method uses three lung datasets for evaluation: LUNA16, Lung CT Segmentation Challenge (LCTSC), and Cancer Genome Atlas Database (CGAD). The experimental results show that the proposed method helps to identify the lung tumour earlier and provides an efficient diagnosis to the patient.