Lung Cancer Classification by Utilizing Various Transfer Learning Model

Globally, lung cancer is seriously threatening to health, set apart by its greatest death rate. Mostly it results from radon gasses and air pollution exposure, emphasized as one of the practical issues for implementing DL models in clinical settings. This work uses several Deep Learning models to detect the disease timely, under VGG16, InceptionV3, and EfficientB0. Early lung cancer prediction can lower the death rate as well as be beneficial in treatment. To produce a more dependable and efficient output, every method has different features that can help the model to predict lung cancer timely. EfficientNetB0 performs better than other models with 93% accuracy and a minimum loss of 0.234 since it has a different scaling ability to train the model. The effectiveness of DL models in forecasting disease and describing the uniqueness of the DL models is based on their Deep Neural Networks.