We are excited to share the release of our latest paper titled, “Histological proven AI performance in the UKLS CT lung cancer screening study: Potential for workload reduction”. This study, conducted in collaboration with researchers from the University of Liverpool, explores the role of artificial intelligence (AI) and its potential to revolutionize radiology workflows in lung cancer screening.
📊 Key Findings:
🔹 1252 UKLS trial baseline CT scans were used to validate an AI LCS software.
🔹 Radiologist CT-reading workload can be reduced by up to 79 %.
🔹 AI detected all 31 baseline-round lung cancers, NPV 99.8 % (95 %CI 99.0–99.9 %).
💡 What does this mean?
AI as a first-reader in lung cancer screening could significantly improve efficiency without compromising accuracy—potentially transforming early detection and resource allocation in screening programs.
🗣 Expert Insights:
Professor John Field, lead author and Professor of Molecular Oncology at the University of Liverpool, emphasized the significance of the study:
“Implementing low-dose CT screening for lung cancer is highly beneficial, but it comes with logistical and financial challenges. Our research suggests that AI could play a crucial role in making screening programs more efficient while maintaining diagnostic confidence.”
Co-lead author Professor Matthijs Oudkerk, Professor Emeritus of Radiology at the University of Groningen and Chief Scientific Officer of the Institute for Diagnostic Accuracy, highlighted the groundbreaking nature of the research:
“This is the first chest AI validation study performed in a real-world consecutive lung cancer screening program, with histological proven outcomes of lung cancer and a more than 5-years follow-up for disease free survival. Therefore, a milestone for further AI validation in terms of methodology and accuracy with results that can be translated to medical implementation.”
The paper, ‘Histological Proven AI Performance in the UKLS CT Lung Cancer Screening Study: Potential for Workload Reduction’, was published in the European Journal of Cancer (DOI:10.1016/j.ejca.2025.115324).
Check also the recent post by the University of Liverpool: https://lnkd.in/dBz-Ugwv
