Hybrid Deep Learning Segmentation Method on Chest Radiograph Images for Lung Cancer Detection

Chronic pulmonary diseases and lung cancer have become major respiratory concerns in the past decade. Their growing importance emphasizes their impact on public health and the need for better understanding, identification, and control. They increased deaths in India and abroad. High teen and adult smoking rates cause these events. Saving lives requires identifying lung cancer and COPD. Fast and effective diagnosis and treatment of the two disorders. This study employs chest radiographs, neural networks with artificial intelligence, machine learning algorithms, and deep learning techniques to accurately detect the two most lethal thoracic illnesses. Residual neural networks (ResNets) improve picture feature extraction and sickness classification. This approach analyzes chest radiograph imaging scan datasets with anomalies like tiny lobes or larger respiratory system capillaries better than lung imaging. Advanced AI and DL can provide healthcare monitoring systems with accurate insights and results. The dynamic field of oncology uses deep learning techniques. The research focuses on deep learning segmentation models. A model was created to improve chest radiography and lung cancer detection. Investigations using RID data. Model sensitivity and mean false positive are assessed independently. Compared to leading methods, RadiographNet has improved significantly.