Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{184731,
        author = {Nilesh Gupta and Kishan Kumar},
        title = {Hybrid Convolutional Neural Network and Transformer-Based Deep Learning Approach for Early Lung Cancer Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {3067-3077},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184731},
        abstract = {Lung cancer continues to be among the most common cancers and a major cause of cancer-related deaths globally, thus, stress the need for early detection and accurate diagnosis. In the present paper we propose a Hybrid CNN-Transformer deep learning framework, which combines both the local spatial feature extraction strength of CNN and the ability of global contextual modeling of Transformer for CT-based automated lung cancer detection. For clinical transparency, explainable AI methods, such as Grad-CAM and attention heatmaps, were included for model interpretation. Performance was evaluated on benchmark datasets in experiments as high as 96.8% accuracy, 96.1% precision, 95.7% recall, 95.9% F1-score, and 97.3% AUC., outperforming CNN, Vision Transformer, CNN–RNN Hybrid respectively. The results demonstrate the promise of the proposed framework for computer-aided diagnostic (CAD) systems to provide clinically-meaningful, interpretable and robust decision support in early lung cancer screening.},
        keywords = {Lung Cancer Detection, CNN–Transformer Hybrid, Explainable AI, Deep Learning, Medical Imaging, Computer-Aided Diagnosis.},
        month = {September},
        }