Paper Title
Harnessing Machine Learning for Early Detection of Lung Cancer Using CT Images

Abstract
Lung cancer is one of the deadliest cancers, partly because it’s often found too late. This project aims to create a deep learning system using Convolutional Neural Networks (CNNs) to help detect and classify lung nodules (small growths) in CT scan images automatically. CT scans show detailed images of lung tissue, but analyzing them by hand can be slow and challenging. This model uses CNNs to accurately spot cancerous and non-cancerous nodules. Techniques like image enhancement and data augmentation help the model adapt to different cases, making it more reliable across a range of scenarios. Regularization methods like dropout reduce the risk of overfitting, so the model performs well even with new, unseen cases. It runs efficiently on hospital computers and integrates easily with hospital systems. By continuously learning from new data and clinical feedback, this project strives to make early lung cancer detection faster, more accurate, and more accessible, supporting future advancements in healthcare. Keywords - CNN, LDCT, TM, RAD, Fastai, Resnet, CT, Gradio