AI-Enabled Precision CT Imaging for Early Detection and Classification of Lung Cancer

Abstract

cancer remains one of the leading causes of cancer-related mortality worldwide, and early diagnosis is essential for improving treatment outcomes and patient survival. Computed tomography (CT) plays a vital role in the detection and characterization of pulmonary abnormalities; however, the increasing volume and complexity of imaging data can create substantial challenges for accurate and timely interpretation. Artificial intelligence (AI), particularly deep learning, has emerged as a promising approach for automated medical image analysis and precision diagnosis. This study presents an AI-enabled precision CT imaging framework for the early detection and classification of lung cancer. The proposed framework incorporates image pre-processing, lung-region segmentation, region-of-interest extraction, deep feature learning, and automated classification to identify suspicious pulmonary abnormalities. CT images are initially enhanced through noise reduction, contrast improvement, and intensity normalization to improve image quality and consistency. Lung regions are subsequently isolated using segmentation and morphological operations, followed by convolutional neural network-based feature extraction and classification. The proposed model achieved an accuracy of 95.2%, sensitivity of 94.1%, specificity of 96.0%, precision of 94.8%, F1-score of 94.4%, and ROC-AUC of 0.97. The findings demonstrate the potential of AI-enabled CT imaging to support accurate and efficient identification of lung cancer patterns. By integrating automated image analysis with clinical expertise, the proposed framework may contribute to earlier diagnosis, improved diagnostic consistency, and precision-oriented lung cancer management. Further validation using large and diverse clinical datasets is required before routine clinical implementation.