iCAD Announces Data Supporting Short-Term Breast Cancer Risk Technology

By News Release

iCAD, Inc.,  a provider of cancer detection and therapy solutions, has announced compelling data supporting ProFound AI™ Risk was published in the peer-reviewed journal, Radiology.[i] ProFound AI Risk is the first and only commercially available clinical decision support tool that provides an accurate two-year breast cancer risk estimation that is personalized for each woman, based solely on a screening mammogram. The technology, which allows for the detection of cancers between screenings, was clinically proven to significantly outperform existing breast cancer risk models.

ProFound AI Risk was created from an exclusive relationship between iCAD and leading researchers at the Karolinska Institutet in Stockholm, Sweden, one of the world’s foremost medical research universities and the home of the Nobel Assembly, which selects the Nobel laureates in Physiology or Medicine. This partnership built upon a previous research agreement whereby researchers at the Karolinska Institutet developed a breast cancer risk prediction model using information identified in mammography images provided by iCAD’s AI solutions.

“ProFound AI Risk and the publication of this supporting study represent a giant leap forward in the realm of breast cancer screening. This first-in-kind solution provides crucial data about patients’ individual risk of developing breast cancer between screenings and empowers clinicians to truly personalize patient care,” according to Michael Klein, Chairman and CEO of iCAD. “This technology may help clinicians tailor unique screening regimens for patients, within country guidelines, and may help reduce unnecessary supplemental screenings for women with low risk.”

ProFound AI Risk software uniquely combines aspects within mammographic images, as well as age and breast density, to provide a highly accurate short-term risk estimation that is specific to each woman. The technology provides clinicians with a two-year breast cancer risk category [low, general, moderate and high] and absolute breast cancer risk score for each patient, based on information garnered from a standard bilateral two-view full field digital mammogram.

“ProFound AI empowers women to participate and advocate for the management of their breast care. There is a growing demand among patients to know more information about their individual risk. According to a recent survey, 87% of women expressed interest in learning about their estimated lifetime risk of breast cancer,[ii]” according to Stacey Stevens, President of iCAD. “ProFound AI Risk has the potential to revolutionize the way breast cancer risk is assessed and could contribute to the acceleration of breast cancer screening from what has historically been an aged-based screening paradigm to a risk-adapted screening paradigm, unique to each woman.”

ProFound AI Risk is supported by a recent study led by researchers at the Karolinska Institutet based on the prospective screening cohort, KARolinska MAmmography Project for Risk Prediction of Breast Cancer (KARMA), which recruited women from 2011-2017. Of 70,877 participants in the KARMA cohort, 974 women with incident cancers and 9,376 healthy women were sampled. ProFound AI Risk reached an area under the curve (AUC) of 0.73 (95% CI 0.71, 0.74). AUC is a standard performance measurement for AI technology that incorporates sensitivity and specificity into a single metric of overall performance. ProFound AI Risk’s AUC of 0.73 indicates high accuracy for risk assessment.

“The Profound AI Risk model performs better than any other current model,” according to the study’s principal investigator, Per Hall, MD, Professor/Senior Physician at the Karolinska Institutet. “The model is a short term risk model which is an advantage in the screening setting, builds heavily on analyses of mammograms, has a flexibility that allows users to choose variables included in the model, is easy and cheap to implement and has little requirement of staff and systems to manage the data.”

Researchers also found a statistically significant superior performance when comparing the ProFound AI Risk model to existing risk models at two years, such as the Tyrer-Cusick v8 model (+11 points) or GAIL model (+12 points), all including breast density within their calculations. Researchers concluded ProFound AI Risk identified women at high likelihood of being diagnosed with breast cancer within two years of a negative screen and in possible need of supplemental screening.i

“ProFound AI Risk is a powerful tool that may aid in the detection of interval cancers, or lesions that are detected between routine mammography screenings,” according to Dr. Axel Gräwingholt, Radiologie am Theater, Paderborn, Germany. “In my experience using the technology following its CE Mark approval and launch in Europe earlier this year, I have found it offers valuable insights for clinicians who may be looking to provide a stratified risk assessment for patients, and is easy to use compared to other breast cancer risk models.”

ProFound AI Risk is currently available on an introductory basis for 2D mammography and will subsequently be available for the rapidly growing 3D mammography market. It is the latest addition to iCAD’s Breast Health Solutions suite, which includes ProFound AI™ for Digital Breast Tomosynthesis (DBT), ProFound AI™ for 2D Mammography, and software solutions for breast density. ProFound AI Risk was CE marked and launched in Europe at the European Congress of Radiology (ECR) virtual meeting in July 2020.

“Last year we introduced our initiative, Panorama Powered by ProFound AI, and with ProFound AI Risk, this concept is beginning to come to life,” added Mr. Klein. “iCAD continues to bring innovative solutions like this to market, and we look forward to advancing the field of mammography as we are working to further expand the ProFound AI portfolio to include next-generation technology that will also incorporate patient’s prior images.* The ability to correlate patients’ past and present images along with future risk will provide clinicians with a broader panoramic vision for each patient that will enable them to evaluate findings across time and ultimately lead to more tailored and personalized patient care.”

*Not yet commercially available

[i] Eriksson, M., et al. Identification of Women at High Risk of Breast Cancer Who Need Supplemental Screening. [published online ahead of print September 8, 2020]. Radiology. Accessed via https://doi.org/10.1148/radiol.2020201620

[ii] Amornsiripanitch N, Ameri SM, Goldberg RJ. Impact of Age, Race, and Socioeconomic Status on Women's Perceptions and Preferences Regarding Communication of Estimated Breast Cancer Risk. Academic Radiology. May 2020. Accessed via https://doi.org/10.1016/j.acra.2020.03.041

Back To Top

iCAD Announces Data Supporting Short-Term Breast Cancer Risk Technology.  Appl Radiol. 

By News Release| September 15, 2020

About the Author

News Release

News Release

Copyright © Anderson Publishing 2020