Lung Cancer Detection from CT Scan Images Using AlexNet

Lung cancer is one of the hazardous public health conscious problems and early detection is very much essential for improving patient outcomes. Convolutional Neural Networks (CNNs) have been proved as a promising tool for recognizing lung cancer from medical imaging data, especially from Computed Tomography (CT) scans. In this study, we introduce a method for lung cancer detection with the help of CNN models like AlexNet with CT scan images. The suggested procedure calls for pre-processing the CT scan pictures before feeding them to the CNN model. The components of the model are convolutional, pooling layers and fully connected layers and the model is trained on a dataset of CT scans with annotated lung cancer. However, manual analysis of these images can be time-consuming and prone to human error. regions. The trained model can detect new CT scan images as either affected or not. The performance of the proposed approach is calculated on a LUNA16 dataset of CT scans, and the outcome shows that the AlexNet model accomplishes high accuracy in detecting lung cancer, with an overall accuracy of over 94%. The model also achieves high sensitivity and specificity, indicating that it can accurately detect both cancer effected and affected regions in the lungs. The proposed approach has the required potential to be used as a screening tool for early detection of lung cancer, which could help in improving patient outcomes and reduce the abundance burden of lung cancer on healthcare systems.