Artificial Intelligence (AI) in Mammography Screening (AIM)
Artificial Intelligence in Mammography Screening - AIM is a research program with a particular focus on clinical utility, efficiency, and implementation aspects. The research so far comprises three major sub-studies and is conducted in close collaboration with both academic and industry partners.
Sub-study 1 – AI-ROL
This study investigated the use of AI as a decision-support tool in mammography screening. Data collection was carried out between 2020 and 2021 in close collaboration with ScreenPoint Medical (https://screenpoint-medical.com/). Results show that AI can help reduce radiologists’ workload without compromising patient safety. The study is completed and has been presented at several international conferences, including in Chicago in 2022:
https://www.auntminnie.com/clinical-news/womens-imaging/breast/article/15632437/ai-can-safely-reduce-breast-imaging-workload-as-third-reader
https://www.auntminnie.com/clinical-news/womens-imaging/breast/article/15632437/ai-can-safely-reduce-breast-imaging-workload-as-third-reader
Sub-study 2 – Health Economic Analysis
This study focused on the economic impact of AI in mammography screening. The results indicate substantial potential for cost-efficiency and resource optimization. The study was presented in the spring of 2025 at the European Congress of Radiology (ECR) in Vienna, where it attracted considerable attention:
https://theimagingwire.com/2025/02/27/european-congress-of-radiology-is-underway/
https://theimagingwire.com/2025/02/27/european-congress-of-radiology-is-underway/
Sub-study 3 – VAI-B
VAI-B is a multicenter study based on retrospective data collection from three Swedish regions, including Region Östergötland. The aim is to externally validate AI for clinical use in mammography. Results have been published in several scientific journals, including:
• Nature Digital Medicine (2025)
• Journal of Medical Imaging (2023)
• Läkartidningen (2023)
Two new studies are currently in the planning phase, partly funded by, among others, the Regional Cancer Center Southeast. The overarching goal of the research program is to contribute to the safe, cost-effective, and equitable implementation of AI in Swedish breast cancer screening.
