LOW-DOSE COMPUTED TOMOGRAPHY (LDCT) IN LUNG CANCER SCREENING: EVOLUTION OF CLINICAL EVIDENCE, METHODOLOGY, AND IMPLEMENTATION CHALLENGES

Jakub Chołast; Maurycy Jabłoński; Laura  Kobaka; Wiktoria Łuniewska; Jakub Kacer; Julia Kacer; Jakub Niepokój; Klaudia  Jurga; Marta Modrzyk

doi:10.31435/ijitss.2(50).2026.6028

Authors

Jakub Chołast Lower Silesian Oncology Center, pl. Ludwika Hirszfelda 12, 53-413 Wroclaw, Poland https://orcid.org/0009-0006-7180-2029
Maurycy Jabłoński Poznan University of Medical Sciences, Poznan, Poland https://orcid.org/0009-0006-6793-6534
Laura Kobaka Poznan University of Medical Sciences, Poznan, Poland https://orcid.org/0009-0007-1010-3467
Wiktoria Łuniewska Wroclaw Medical University, Wroclaw, Lower Silesia, Poland https://orcid.org/0009-0009-5398-422X
Jakub Kacer Lower Silesian Oncology Center, pl. Ludwika Hirszfelda 12, 53-413 Wroclaw, Poland https://orcid.org/0009-0005-8573-0815
Julia Kacer Wroclaw Medical University, Wroclaw, Lower Silesia, Poland https://orcid.org/0009-0005-1709-3236
Jakub Niepokój Wroclaw Medical University, Wroclaw, Lower Silesia, Poland https://orcid.org/0009-0003-5273-4532
Klaudia Jurga Poznan University of Medical Sciences, Poznan, Poland https://orcid.org/0009-0004-3676-8166
Marta Modrzyk Institute of Medical Sciences, Opole, Poland https://orcid.org/0009-0003-9590-5602

DOI:

https://doi.org/10.31435/ijitss.2(50).2026.6028

Keywords:

Lung Cancer, Low-Dose Computed Tomography (LDCT), Cancer Screening, Artificial Intelligence, Risk Prediction Models, Early Detection

Abstract

Introduction: Lung cancer is the leading cause of cancer death worldwide‚ with approximately 1․8 million deaths annually (1‚2)․ Lung cancer is a stage-dependent disease‚ with the highest rate of long-term survival in those diagnosed with localized disease‚ especially if amenable to curative resection (1‚3)․ The answer‚ given in two important RCTs‚ the NLST (1) and the NELSON trial (2)‚ is that LDCT screening for lung cancer in high risk individuals reduces specific mortality from lung cancer compared with X-ray and no screening․ Common implementation of screening has proved very difficult due to high false positive rates‚ overdiagnosis‚ and the costs of and burden of diagnostic workup of incidental findings (1‚4)․

Objective: To summarize evidence on the effectiveness of LDCT screening from clinical trials‚ and on emerging artificial intelligence (AI) and personalized risk prediction models that could help overcome implementation challenges and improve participant selection (1‚5)․

Materials and methods: We based our recommendations on a review of the key RCT results‚ meta-analyzes‚ and most recent clinical practice guidelines from the US Preventive Services Task Force (USPSTF)‚ American College of Radiology‚ and International Association for the Study of Lung Cancer‚ published between 1997 and 2025 (4‚ 6)․ A literature search of MEDLINE‚ PubMed‚ and the Cochrane Library was performed‚ reviewing peer-reviewed articles describing screening results‚ nodule management protocols‚ and diagnostic performance of deep learning algorithms (4‚ 7)․

Conclusions: Current evidence supports LDCT screening high-risk populations to reduce lung cancer specific mortality by 16% to 24%(2‚8)․ Optimizing risk-based screening through validated models (e․g․ PLCOm2012)‚ rather than fixed age and smoking criteria‚ is important to avoid unnecessary screening‚ costs‚ and potential harms(3‚5)․ Screening protocols should prioritize high-risk individuals‚ regardless of their age or smoking status․ Artificial intelligence is another promising development‚ which can improve the classification of benign and malignant nodules‚ automate the process of image interpretation‚ and reduce the work of radiologists (1‚5)․ Global implementation is likely to require the use of standardized reporting (Lung-RADS)‚ smoking cessation programs‚ and strategies for equitable access to screening (2‚5)․

References

De Luca, G. R., Diciotti, S., & Mascalchi, M. (2025). The pivotal role of baseline LDCT for lung cancer screening in the era of artificial intelligence. Archivos de Bronconeumología, 61(6), 359–367.

Lam, S., Bai, C., Baldwin, D. R., Chen, Y., Connolly, C., de Koning, H., et al. (2024). Current and future perspectives on computed tomography screening for lung cancer: A roadmap from 2023 to 2027 from the International Association for the Study of Lung Cancer. Journal of Thoracic Oncology, 19(1), 36–51.

Ramaswamy, A. (2022). Lung cancer screening: Review and 2021 update. Current Pulmonology Reports, 11(1), 15–28.

Bonney, A., Malouf, R., Marchal, C., Manners, D., Fong, K. M., Marshall, H. M., et al. (2022). Impact of low-dose computed tomography (LDCT) screening on lung cancer-related mortality. Cochrane Database of Systematic Reviews, 2022(8), Article CD013829.

Lancaster, H. L., Heuvelmans, M. A., & Oudkerk, M. (2022). Low-dose computed tomography lung cancer screening: Clinical evidence and implementation research. Journal of Internal Medicine, 292(1), 68–80.

Manuel, L., Fong, L. S., Ly, T., & Meredith, G. (2021). Does lung cancer screening with low-dose computerized tomography improve survival? Interactive Cardiovascular and Thoracic Surgery, 33(5), 741–745.

Hoffman, R. M., Atallah, R. P., Struble, R. D., & Badgett, R. G. (2020). Lung cancer screening with low-dose CT: A meta-analysis. Journal of General Internal Medicine, 35(10), 3015–3025.

Sakoda, L. C., & Henderson, L. M. (2025). Updates in lung cancer screening: A decade of evidence. Seminars in Respiratory and Critical Care Medicine, 46(5), 502–519.

Wu, Z., Wang, F., Cao, W., Qin, C., Dong, X., Yang, Z., et al. (2022). Lung cancer risk prediction models based on pulmonary nodules: A systematic review. Thoracic Cancer, 13(5), 664–677.

Teles, G. B. da S., Macedo, A. C. S., Chate, R. C., Valente, V. A. T., Funari, M. B. de G., & Szarf, G. (2020). LDCT lung cancer screening in populations at different risk for lung cancer. BMJ Open Respiratory Research, 7(1).

Mikhael, P. G., Wohlwend, J., Yala, A., Karstens, L., Xiang, J., Takigami, A. K., et al. (2023). Sybil: A validated deep learning model to predict future lung cancer risk from a single low-dose chest computed tomography. Journal of Clinical Oncology, 41(12), 2191–2200.

Wang, C., Chen, B., Liang, S., Shao, J., Li, J., Yang, L., et al. (2025). China protocol for early screening, precise diagnosis, and individualized treatment of lung cancer. Signal Transduction and Targeted Therapy, 10(1), Article 175.

Leonard, S., Patel, M. A., Zhou, Z., Le, H., Mondal, P., & Adams, S. J. (2025). Comparing artificial intelligence and traditional regression models in lung cancer risk prediction using a systematic review and meta-analysis. Journal of the American College of Radiology, 22(6), 675–690.

Chang, H.-T., Wang, P.-H., Chen, W.-F., & Lin, C.-J. (2022). Risk assessment of early lung cancer with LDCT and health examinations. International Journal of Environmental Research and Public Health, 19(8).

Chen, K.-H., Lin, Y.-H., Wu, S., Shih, N.-W., Meng, H.-C., Lin, Y.-Y., et al. (2025). NLSTseg: A pixel-level lung cancer dataset based on NLST LDCT images. Scientific Data, 12(1), Article 1475.