AI Reduces CT Lung Cancer Screening Workload by Almost 80%

Lung cancer impacts over 48,000 individuals in the UK annually, and early detection is key to improving survival rates. The UK Lung Cancer Screening (UKLS) trial has already shown that low-dose CT (LDCT) screening can save lives by identifying lung cancer in high-risk individuals before symptoms arise. Now, a recent study has demonstrated that artificial intelligence (AI) can greatly enhance the efficiency of lung cancer screening. Published in the European Journal of Cancer, the study indicates that AI can accurately rule out negative LDCT scans, potentially reducing the radiologist’s workload by up to 79%.

In this latest study, researchers from the University of Liverpool (iDNA, Liverpool, UK) and the Research Institute for Diagnostic Accuracy (Groningen, The Netherlands) tested an AI tool developed by Coreline Soft (Seoul, South Korea) using data from the UKLS trial. The AI effectively identified scans without significant lung nodules—accounting for the majority of cases—even among high-risk individuals. This capability allows radiologists to direct their expertise toward cases needing further examination, thereby improving efficiency while maintaining high accuracy in lung cancer detection.

Image: Histologically confirmed lung cancer cases detected at immediate referral after baseline scan or 3-month short-term follow-up (Photo courtesy of DOI:10.1016/j.ejca.2025.115324)

A key finding of the study was that all confirmed lung cancer cases were found among scans flagged by the AI for additional review. This ensures that no cancers were overlooked while significantly decreasing the number of scans requiring manual evaluation. The success of the study was supported by the high-quality radiology reports from the UKLS trial and its long-term follow-up data, which offered a dependable dataset for validating the AI model. Lung cancer screening programs are expanding globally, and AI-powered tools like the one evaluated in this research could play a crucial role in optimizing healthcare resources, lowering costs, and ensuring timely diagnoses. Additional research and validation studies will be necessary to further refine these AI models.

“Implementing low-dose CT screening for lung cancer is highly beneficial, but it comes with logistical and financial challenges,” said Professor John Field, lead author and Professor of Molecular Oncology at the University of Liverpool. “Our research suggests that AI could play a crucial role in making screening programs more efficient while maintaining diagnostic confidence.”