Skip to main content
News and Products

iCAD partners with Karolinska to develop AI-based breast cancer risk prediction system

iCAD have entered into an exclusive relationship with two leading researchers at The Karolinska Institutet in Stockholm, Sweden, to develop an artificial intelligence (AI)-based solution that will identify a women’s individual risk of developing breast cancer. This partnership builds on an existing research agreement in which the researchers at the Karolinska developed a breast cancer risk prediction model using information identified in mammography images provided by iCAD’s AI cancer detection and density assessment solutions. Promising early results based on mammography images from over 70,000 Swedish women enrolled in The Karolinska Mammography Project for Risk Prediction of Breast Cancer (Karma) study indicated that the model enabled early identification of women who were at a high-risk for breast cancer and it was determined that additional examinations were warranted. The Karma results have been improved upon through the use of iCAD’s latest ProFound AI algorithm. Among other things, the model now takes asymmetry of mammographic features and masking of tumors into consideration. iCAD and the Karolinska researchers now intend to collaborate to develop an innovative solution for commercial use to assess an individual’s risk of developing breast cancer.

Breast cancer is the most prevalent cancer among women worldwide, impacting over 2 million women each year. Breast cancer screening and early detection are key to improving outcomes and survival rates. However, today, most mammography screening programs are not individualized, so a significant need exists to be able to identify individual risk of the disease in order to most effectively screen for breast cancer.

Models that accurately predict an individual woman’s risk of developing breast cancer are paramount to transitioning from age-based screening to risk-based screening,” said Per Hall, Professor, Senior Physician, Karolinska Institutet. “Most current risk models are population-based and focus on lifetime or long-term risk. Our research using the iCAD AI technology has shown that by simply using the information available in the mammogram images, we can more accurately stratify women based on short-term risk. Understanding short-term risk will open the door to new paradigms in both the prevention and treatment of breast cancer.”

iCAD announced the commercial availability of its ProFound AI for breast cancer detection in digital breast tomosynthesis in 2018. This delivers critical benefits, including improvement in cancer detection rates, a decrease in unnecessary patient recalls, and shorter reading times for radiologists.

We envision the field of mammography moving from age-based screening protocols to “risk adaptive screening.” Concurrently, we foresee the emergence of individualized breast screening protocols based on risk characteristics,” said Mike Klein, Executive Chairman and CEO of iCAD. “This new frontier of predictive risk assessment for cancer is indicative of the continued expansion of our newly released ProFound AI offering for breast cancer detection. Correlating iCAD’s high cancer detection rates, low false positive levels and a 50% reduction in reading time with the burgeoning volume of patent risk data, may provide a quantum leap in clinical efficacy and patient care


Nashua, NH, USA