Lung Cancer Detection using 3D U-Net Based DENSENET with Multimodal Images CT Scans and Histopathological Images

Lung cancer detection is an important component of medical imaging aimed at early detection and optimal clinical outcomes. This study presents a novel approach using 3D U-Net based Dense Net architecture, using more data from computed tomography (CT) scans and histopathologic images to increase detection accuracy 3D U-Net capture spatial features and facilitate the accurate classification of lung tumors, while the Dense Net component Effective reuse of features between layers strengthens the model, deeper coding features promote exclusion This multimodality aims to bridge the gap between radiologic and pathologic assessment, providing comprehensive information and a reliable tool for early lung cancer diagnosis and treatment with a personalized treatment plan. The classifiers will be compared on their precisions with other models referred to from existing literature. Finally the accuracy of the proposed classifier is compared with other models from the existing literature. The introduced approach aims to achieve accurate and efficient lung cancer detection through the 3D U-Net-based Dense Net method. The developed approach has great potential in the analysis of medical imaging for diagnosis. The experimental results are promising, which verifies the utility of the proposed approach to identify cancerous regions in chest CT images accurately.