Copyright © 2026 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{187230,
        author = {Vishwajeet Mane and Shantanu Sarnaik and Mukesh Hiwarkar and Ziya Balbhude and Prof. Leelkanth Dewangan},
        title = {AI-Based Diagnostic Systems for Lung Cancer: Innovations, Challenges, and Future Perspectives},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {4077-4085},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187230},
        abstract = {Lung cancer remains one of the leading causes of cancer-related deaths worldwide, with patient prognosis heavily reliant on timely diagnosis. Recent advancements in artificial intelligence (AI), particularly through deep learning and machine learning (ML) approaches, have significantly transformed diagnostic imaging and early detection strategies. This review consolidates studies utilizing AI-driven methods ranging from classical ML algorithms including traditional machine learning models, for example, support vector machines and artificial neural networks, as well as modern deep learning architectures such as convolutional neural networks, applied for the detection, segmentation, and classification of pulmonary nodules.
A fully automated AI platform employing [18F] fluorodeoxyglucose (FDG) PET-CT imaging has demonstrated high sensitivity (90%) in detecting abnormal lung lesions and precisely estimating total lesion glycolysis (TLG), showing strong concordance with manual evaluations [23]. Systematic analyses of 39 studies further highlight AI’s clinical utility, with pooled diagnostic sensitivity and specificity approaching 87% [14]. Deep learning models, particularly CNNs, have surpassed conventional CAD systems in distinguishing benign from malignant lung tissue, facilitating early intervention and enhancing patient outcomes [15], [16].
Although challenges remain, including model validation and standardization, AI-based diagnostic platforms provide a transformative avenue for lung cancer detection improving diagnostic precision, streamlining clinical workflows, and supporting personalized patient management.},
        keywords = {AI, Lung Cancer, FDG PET-CT, Deep Learning, CNN, Diagnostic Imaging, Pulmonary Nodule, Total Lesion Glycolysis, Machine Learning, Early Detection},
        month = {November},
        }