AI Boosts Breast Cancer Detection in Dutch Screening Program
Artificial intelligence is proving to be a powerful tool in the detection of breast cancer within the Dutch national screening program. Recent research from Radboudumc demonstrates that AI not only accelerates tumor revelation but also has the potential to reduce the burden on radiologists and generate significant cost savings.
Study Details
Led by breast radiologist Ritse Mann at Radboudumc,the study analyzed over 42,000 mammograms from women in the utrecht region. In a standard review, two radiologists independently assess each image. However, in this research, an AI system developed by Screenpoint Medical was also utilized. The women involved were monitored for nearly 4.5 years wiht follow-up examinations.
Enhanced Accuracy Through Collaboration
The findings reveal that combining the expertise of a radiologist with AI results in a higher rate of tumor detection compared to relying on two radiologists alone. critically, the AI-assisted approach also led to the identification of tumors at an earlier stage, enabling quicker initiation of treatment.
Cost and Workload Reduction
Researchers estimate that widespread adoption of AI in breast cancer screening could save millions of euros annually while together easing the workload pressures faced by radiologists. Currently, however, AI is not yet standard practice in the Netherlands. “The IT capacity is not yet there.Extra money is needed for that,” explains Mann.
Successful Implementation in Sweden
Sweden is already implementing a similar model, where the AI system effectively replaces the role of the second radiologist. A human radiologist is only consulted when the AI flags an image for further review. “We see that the collaboration between AI and radiologists is going well. More tumors are being traced, without unnecessarily many women having to come back for extra checks,” Mann notes.
Source: ANP, Radboudumc, The Lancet Digital Health
