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{181902,
        author = {DR.R.MALATHI RAVINDRAN},
        title = {Optimizing Early Lung Cancer Detection on Chest Radiographs: AI-Based Lung Segmentation for Enhanced Diagnostic Accuracy},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {98-102},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181902},
        abstract = {Early detection of lung cancer significantly improves survival rates, yet interpreting chest radiographs (CXR) remains challenging due to overlapping anatomical structures. This study proposes an AI-based segmentation framework using U-Net to isolate lung regions, enhancing the performance of subsequent nodule detection models. We trained and evaluated the model on publicly available Montgomery and Shenzhen datasets, achieving a Dice coefficient of 0.961 and IoU of 0.924. Further classification on the JSRT dataset demonstrated improved sensitivity and specificity in nodule detection when lung segmentation was applied. This work affirms that AI-based lung segmentation significantly improves early lung cancer diagnostic accuracy and provides a foundation for scalable computer-aided diagnosis systems.},
        keywords = {Chest Radiograph, Deep Learning, Early Detection, Lung Cancer, Segmentation, U-Net.},
        month = {June},
        }