LUN-Net: Deep Learning Approach Based Medical Image Processing for Lung Cancer Detection

This research study proposes LUN-Net, a deep learning-based method for lung cancer detection, which represents a substantial breakthrough in medical image processing. Using transfer learning techniques on the C19RD and CXIP datasets, the goal of this research is to develop an end-to-end model that can accurately diagnose different kinds of lung cancer using CT scans. LUN-Net seeks to deliver accurate and dependable classifications by combining feature extraction and optimizing pre-trained models like VGG16, MobileNet, DenseNet, Inception V3, and AlexNet. This approach ensures optimal performance in medical image analysis by investigating the effects of different activation functions. Improving diagnostic efficiency and accuracy is the main objective, which will greatly aid in the early diagnosis of lung cancer. In order to improve the results of lung cancer treatment, this research emphasizes the promise of deep learning in medical diagnostics and emphasizes the significance of utilizing reliable models and extensive datasets. By pushing the limits of AI in healthcare, this research study intends to save lives by promoting earlier and more accurate lung cancer diagnoses.