Combining Multi-Features for Lung Cancer Detection in Computed Tomography Images: A Feature Fusion Model

Lung cancer is a leading cause of cancer-related deaths worldwide, emphasizing the importance of early detection. Although Computed Tomography (CT) images are widely used for diagnosing lung cancer, their high dimensionality and variability can pose challenges to accurate detection. In light of this, we have developed a novel approach to lung cancer detection using CT images, leveraging a feature fusion model. Our model integrates multiple features extracted from the images using ResNet152, EfficientNetB4, and XceptionNet to improve detection accuracy. We evaluated our model using a vast dataset of CT images and associated its performance to traditional and techniques based on deep learning that are up-to-date. The results demonstrate that our proposed feature fusion model outperforms other methods, achieving high accuracy, sensitivity, and specificity. This approach has enormous potential for improving the early detection of lung cancer, ultimately contributing to developing more effective treatment strategies.