New advances in cancer screening were among the major trends at last week’s ECR 2025 conference in Vienna. From traditional screening exams like mammography to up-and-coming tests like CT lung cancer exams, radiologists are emerging at the forefront of efforts to improve population health through early detection.
CT lung cancer screening is gaining momentum in Europe, and a Friday afternoon session explored the experiences of multiple sites…
- U.K. researchers used DeepHealth’s Lung Nodules AI solution for automated triage of lung nodules found on non-screening CT chest exams, finding the approach could save £25k-£37k annually.
- A German team documented technical lung CT acquisition parameters for screening centers in the SOLACE consortium across 10 countries, finding some room for improvement.
- Preliminary results from an Italian lung screening project were reported, with 2k people scanned with a 1.5% cancer detection rate (77% stage I-II) and 17% recall rate. Smoking cessation advice was also given.
- Early results from a pilot screening project in Poland were given, with a 1.9% cancer detection rate in 3.1k people screened. They recommend screening be implemented nationwide.
- In a secondary analysis of 23.4k people in the NLST study, CT-derived body composition metrics predicted mortality beyond traditional risk factors.
Meanwhile, new ECR cancer screening research builds on the landmark accomplishments from 2024 in AI for breast screening. A Saturday afternoon session explored the progress being made…
- German breast screening programs that deployed ScreenPoint Medical’s Transpara AI algorithm for 119k women saw their cancer detection rate grow (6 vs. 4.8 cancers per 1k) while the recall rate remained stable at around 2.5%.
- AI-supported double-reading in Italy for 120k women led to more breast cancers detected on baseline exams compared to subsequent screening rounds, as well as a 42% lower recall rate.
- Patients found an AI chatbot based on GPT-4 generated responses to their questions that were more empathetic and readable than those of radiologists.
- Another Italian study found that using AI for double-reading mammograms of 266k women led to a 21% increase in cancer detection rate and 15% drop in recall rate.
- A secondary analysis of the MASAI trial suggested that double-reading with two radiologists continue to be used for high-risk women. Single reading of 3.8k high-risk exams resulted in 8.9% fewer detected cancers and 5.9% fewer recalls.
The Takeaway
Last week’s research on cancer screening at ECR 2025 shows that imaging experts see screening as a way to not only improve population health on a broad scale, but also to give radiologists the opportunity to raise their profile with patients and take a more direct role in patient care. The question is whether it’s an opportunity radiologists are ready to take.
