Lung Cancer Detection Using Deep Learning Model

Lung cancer is one of the leading causes of cancer-related mortality worldwide, and early detection significantly improves patient survival rates. Traditional diagnostic methods such as CT-scan interpretation are time-consuming and require high clinical expertise. In this project, we propose an automated lung cancer detection system using an Attention-Enhanced Inception NeXt–based deep learning model. The model integrates the representational efficiency of the Inception NeXt architecture with an attention mechanism that highlights discriminative lung regions, enabling more accurate identification of cancerous nodules A pre-processed dataset of CT scan images is used to train and evaluate the model. Image augmentation, normalization, and lung-region enhancement techniques are applied to improve data quality and reduce overfitting. The proposed hybrid architecture demonstrates superior feature extraction capabilities and improved sensitivity compared to conventional CNNs. Experimental results indicate that the model achieves high accuracy, precision, recall, and F1-score, making it a reliable tool for assisting radiologists in early lung cancer diagnosis. This system has the potential to support faster, more consistent, and more accurate clinical decision-making.