Gradient-driven pixel connectivity convolutional neural networks classification based on U-Net lung nodule segmentation

Abstract

• Integration of AI in medical imaging holds promise for more precise and efficient lung cancer screening. • The deep learning-based lung nodule detection system achieved remarkable segmentation accuracy (99.16%) using the U-Net algorithm. • The proposed methodology combines semantic segmentation with the U-Net algorithm and classification using a CNN. • Noteworthy results include high accuracy in classifying nodules versus non-nodules (90.36%), subsolid nodules (91.89%), and malignancy of nodules (91.54%). • Results suggest potential advancements in early lung cancer detection and diagnosis. • The study emphasizes the valuable contribution of AI tools in transforming lung tumor screening, offering promise for significant improvements in patient outcomes. Lung cancer is a significant global health issue, heavily burdening healthcare systems. Early detection is crucial for improving patient outcomes. This study proposes a diagnostic aid system for the early detection and classification of lung nodules from Computed Tomography images using deep learning , based on the LUNA16 Dataset. The methodology involves three key steps. Initially, a U-Net convolutional neural network is used for semantic segmentation, followed by feature s extraction and selection, which are subsequently used in classification with another convolutional neural network. The segmentation using the U-Net algorithm achieved an accuracy of 99.16% and a Dice Similarity Coefficient of 88.44%. For distinguishing between nodules and non-nodules in regions of interest, the classification accuracy was 90.36%. Further classification achieved 91.89% accuracy in differentiating solid and ground glass nodules and 91.54% in distinguishing between benign and malignant ones. These results demonstrate the model's robust performance in categorizing various nodule characteristics. These findings highlight the potential of the proposed system as a valuable tool for clinicians, contributing to improved healthcare outcomes and advancing lung cancer diagnosis and treatment.