Deep Learning-Based Lung Cancer Detection Enhancing Early Diagnosis and Treatment Outcomes

As a result of late detection, treatment efficacy is limited, and survival rates are low, lung cancer continues to be a major global health concern. Convolutional Neural Network and pretrained convolutional neural networks (CNN) architectures - VGG-16, InceptionV3, and EfficientNetB0 which is based on Transfer learning is used for the task of lung cancer detection. The photos in the dataset are separated into test, validation, and training sets. During training, we use data augmentation approaches to make the models more resilient and broadly applicable. Model performance is evaluated using accuracy and loss metrics on the test set. The results demonstrate the effectiveness of the transfer learning based model, with EfficientNetB0 achieving the highest accuracy of 94% on the test set. This work demonstrates how deep learning models may be used to diagnose and classify chest CT scan pictures, which could lead to better lung cancer treatment and detection outcomes.