Identifying Lung Cancer from CT-Scan Images with VGG16 Convolutional Neural Net

Lung cancer has become common nowadays resulting cancer related fatalities both in men and women worldwide. Tobacco smoking plays a major role in spread of lung cancer but non-smokers through passive smoking can also have this disease. Physicians employ computed tomography (CT) scans to identify lung cancer in patients and provide appropriate treatment. CNNs have been proved to perform image analysis effectively. In the proposed work, VGG16 model is trained and built on different CT scan images of four categories namely, Adenocarcinoma, Large Cell Carcinoma, Squamous Cell Carcinoma and Normal. Model is pretrained on imagenet. To assess the model's performance, many metrics are employed. The suggested model achieves 92% average recall, precision, and F1 Score and 91% accuracy. Using deep learning approaches, the results can be used to diagnose lung cancer from CT scan images.