Advanced Deep Learning Approaches for Accurate Lung Cancer Detection in Computed Tomography Imaging

Lung cancer continues to be a leading cause of cancer-related deaths globally, with survival rates heavily dependent on early and accurate diagnosis. Detecting the disease in its early stages is vital for increasing patient survival, but this is often hindered by a shortage of radiologists and the increasing volume of medical imaging data. This work explores the application of deep learning methods specifically Convolutional Neural Networks (CNNs) and the VGGNet model for detecting lung cancer using CT scan images. These neural networks are adept at interpreting complex imaging data and can detect minute irregularities that may signal cancer. The integration of CNNs for feature extraction with VGGNet’s layered analysis improves diagnostic precision and minimizes false detection rates. Furthermore, to achieve precise segmentation of lung nodules, an enhanced U-Net model is utilized, recognized for its proficiency in preserving spatial details and producing detailed, high-resolution segmentation outputs.