Artificial intelligence for lung cancer detection: descriptive review of recent studies (2021–2025).
Keywords:
Lung cancer, Diagnosis, Computed tomography (CT), Positron emission tomography (PET), X-rays, Artificial intelligenceAbstract
Lung cancer is one of the leading causes of mortality worldwide, and its early detection is key to improving survival rates. This review synthesizes recent studies (2021–2025) on the use of artificial intelligence (AI) in the early diagnosis of lung cancer, mainly through medical image analysis. Articles were collected from databases such as Scopus, MDPI, and Google Scholar, in both Spanish and English, employing deep or machine learning models. The results highlight architectures such as EfficientNet and CNN+ViTs applied to computed tomography, achieving accuracies above 98\%, while classical algorithms like XGBoost and SVM also show strong performance on clinical data. However, limitations were identified regarding the lack of representative data, use of synthetic data, and absence of external validation. Overall, the evidence confirms AI’s potential to enhance early diagnosis, though greater methodological robustness and clinical validation are still required.
Downloads
References
S. Wankhade y V. S., “A novel hybrid deep learning method for early detection of lung cancer using neural networks”, Healthcare Analytics, vol. 3, p´ag. 100 195, 2023, issn: 2772- 4425. doi: https://doi.org/10.1016/j.health.2023.100195. direcci´on: https://www.sciencedirect.com/science/article/pii/S277244252300062X.
E. Dritsas y M. Trigka, “Lung Cancer Risk Prediction with Machine Learning Models”, Big Data and Cognitive Computing, vol. 6, n.o 4, 2022, issn: 2504-2289. direcci´on: https://www.mdpi.com/2504-2289/6/4/139.
R. Raza et al., “Lung-EffNet: Lung cancer classification using EfficientNet from CT-scanimages”, Engineering Applications of Artificial Intelligence, vol. 126, p´ag. 106 902, 2023, issn: 0952-1976. doi: https://doi.org/10.1016/j.engappai.2023.106902. direcci´on: https: //www.sciencedirect.com/science/article/pii/S0952197623010862.
A. R. Wahab Sait, “Lung Cancer Detection Model Using Deep Learning Technique”, Applied Sciences, vol. 13, n.o 22, 2023, issn: 2076-3417. doi: 10 . 3390 / app132212510. direcci´on: https://www.mdpi.com/2076-3417/13/22/12510.
V. Sreeprada y D. K. Vedavathi, “Lung Cancer Detection from X-Ray Images using Hybrid Deep Learning Technique”, Procedia Computer Science, vol. 230, p´ags. 467-474, 2023, 3rd International Conference on Evolutionary Computing and Mobile Sustainable Networks (ICECMSN 2023), issn: 1877-0509. doi: https://doi.org/10.1016/j.procs.2023.12.102. direcci´on: https://www.sciencedirect.com/science/article/pii/S1877050923021075.
D. Srivastava et al., “Early Detection of Lung Nodules Using a Revolutionized Deep Learning Model”, Diagnostics, vol. 13, n.o 22, 2023, issn: 2075-4418. doi: 10.3390/diagnostics13223485. direcci´on: https://www.mdpi.com/2075-4418/13/22/3485.
A. Agarwal, K. Patni y R. D, “Lung Cancer Detection and Classification Based on Alexnet CNN”, en 2021 6th International Conference on Communication and Electronics Systems (ICCES), 2021, p´ags. 1390-1397. doi: 10.1109/ICCES51350.2021.9489033.
M. Bhuiyan et al., “Advancements in Early Detection of Lung Cancer in Public Health: A Comprehensive Study Utilizing Machine Learning Algorithms and Predictive Models”, Journal of Computer Science and Technology Studies, vol. 6, p´ags. 113-121, ene. de 2024. doi: 10.32996/jcsts.2024.6.1.12.
B. Ozdemir, E. Aslan e I. Pacal, “Attention Enhanced InceptionNeXt-Based Hybrid Deep Learning Model for Lung Cancer Detection”, IEEE Access, vol. 13, p´ags. 27 050-27 069, 2025. doi: 10.1109/ACCESS.2025.3539122.
A. Saha, S. M. Ganie, P. K. D. Pramanik, R. K. Yadav, S. Mallik y Z. Zhao, “VER-Net: a
hybrid transfer learning model for lung cancer detection using CT scan images”, BMC Medical Imaging, vol. 24, n.o 1, p´ag. 120, mayo de 2024, issn: 1471-2342. doi: 10.1186/s12880-02401238-z. direcci´on: https://doi.org/10.1186/s12880-024-01238-z
Downloads
Published
Data Availability Statement
The reviewed articles can be found in the references section, where they can be accessed via the links provided in that section.
