Deep Learning Classification Based Fast Segmentation for Detection of Lung Cancer

Abstract

Lung cancer remains one of the leading causes of cancer-related mortality worldwide, necessitating early and accurate diagnosis for improved patient survival. This paper proposes a Deep Learning Classification-Based Fast Segmentation (DLC-FS) framework for efficient detection and segmentation of lung cancer from computed tomography (CT) images. The proposed method integrates a lightweight convolutional neural network (CNN) classifier with an optimized U-Net-based segmentation architecture to achieve high accuracy with reduced computational complexity. The framework employs advanced preprocessing techniques, including normalization, noise reduction, and contrast enhancement, followed by feature extraction using deep convolutional layers. A hybrid loss function combining Dice loss and binary cross-entropy is utilized to improve segmentation precision. The model is trained and evaluated on publicly available lung cancer datasets, achieving a classification accuracy of 97.8%, precision of 96.5%, recall of 95.9%, and an F1-score of 96.2%. For segmentation performance, the proposed approach attains a Dice Similarity Coefficient (DSC) of 94.7%, Intersection over Union (IoU) of 92.3%, and reduces inference time by 28% compared to conventional U-Net models. Experimental results demonstrate that the proposed DLC-FS framework significantly outperforms existing state-of-the-art methods in both detection accuracy and computational efficiency. The fast segmentation capability makes the system suitable for real-time clinical applications, assisting radiologists in early diagnosis and treatment planning. Future work will focus on multi-modal data integration and deployment in edge-based healthcare systems.