iCAD, Inc. recently launched ProFound AI® Risk for digital breast
tomosynthesis (DBT), or 3D mammography, the world’s first commercially
available clinical decision support tool that provides an accurate[1],[2]
short-term breast cancer risk estimation that is truly personalized for each
woman, based only on a 2D or 3D mammogram. The latest version of this software offers improved accuracy
and enhanced functionality compared to previous versions.
“ProFound AI Risk has the
potential to truly transform personalized breast cancer screening and risk
stratification as we know it,” said Stacey Stevens, President of iCAD, Inc. “We
believe this technology will lead to more appropriate utilization of
supplemental imaging and biopsies, less anxiety for women, and decreased costs
to the system overall. We believe this solution will be increasingly relevant
in the years ahead, as
mammography begins to transition from what is primarily an age-based screening
paradigm today to a more effective and efficient risk-adjusted screening
paradigm.”
The latest generation of ProFound AI Risk offers the ability to
calculate a short-term risk estimation for 3D mammography, with greater
accuracy compared to both the previous version of the risk software based on 2D
mammography and traditionally used risk models. The latest version of ProFound
AI Risk offers expanded features, including:
- The ability to calculate
short-term (one-, two- or three-year) absolute risk based on either 2D or 3D
mammography images. - The ability to factor in
clinically relevant global screening guidelines and more than 15 country
incidence and mortality reference tables, including ethnicities, for alignment
with that country’s general population.
“Factoring in a woman’s racial and ethnic background adds another
dimension of personalization that allows clinicians to stratify risk in a more
inclusive way,” added Stevens. “Studies show African American women have an approximately 40% higher risk of dying
from breast cancer, and they are disproportionately affected by more aggressive subtypes,
such as triple-negative breast cancer and inflammatory breast cancer, compared to
white women.[3],[4],[5] The latest generation of ProFound AI Risk offers the potential to include racial and ethnic backgrounds for further refinement of the image-based model, as well as the incidence and mortality rates for a specific geographic region.”
ProFound AI Risk utilizes breast complexity findings, automated breast
density and age in order to calculate a woman’s short-term, absolute risk of
breast cancer. All of this information is within a woman’s screening mammogram,
making risk assessment simple. Results include the woman’s absolute breast
cancer risk score and breast cancer risk category [low, general, moderate and
high].
“The need for technology
like this has never been greater. The COVID pandemic truly highlighted the
absence of a practical solution to accurately determine an individual’s risk of
developing breast cancer between screenings, as several medical societies
recommended last year that women of ‘average risk’ postpone mammograms. The
issue is, most women simply don’t know their risk,” added Stevens. “As clinicians and facilities recover from the impact of the pandemic
this year, they are presented with unprecedented challenges, including a
significant reduction in patient volume, loss of income, and a growing
mammography backlog. This technology offers a viable solution for the challenges clinicians are
facing today and offers a solution that will remain relevant for years to
come.”
Regular, age-based
mammography screening reduces breast cancer mortality by approximately 20%,[6]
but screening mammography can still miss 20 to 40% of breast cancers.[7],[8]
Many of these cancers are diagnosed as interval breast cancers, defined as
those that emerge after a normal mammogram but before the woman’s next
scheduled screening. These tumors are often diagnosed at a later stage than
cancers detected by screening, and are associated with an increased risk
of breast cancer-specific mortality, compared with cancers detected by
screening.[9]
Clinicians have
traditionally considered risk factors such as family history as a way to assess
women’s risks of developing breast cancer, but about 85% of breast cancers
occur in women who have no family history of breast cancer.[10]
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.
“This leading-edge algorithm was designed to provide physicians with
crucial information about a woman’s short-term risk of being diagnosed with
breast cancer, so that they may further personalize her screening and
surveillance plan. This may include screening frequency adjustment,
supplemental imaging, genetic testing and/or risk reduction strategies,”
according to Per Hall, MD, Professor/Senior Physician, Karolinska Institutet.
“Ultimately, the goal of this technology is to enhance efficiency for
clinicians and improve outcomes for patients.”
###
[1] iCAD data on file.
[2] Eriksson M, Czene K,
Strand F, Zackrisson S, Lindholm P, Lång K, Förnvik D, Sartor H, Mavaddat N,
Easton D, Hall P. Identification of Women at High Risk of Breast Cancer Who
Need Supplemental Screening. Radiology. 2020 Nov;297(2):327-333. doi: 10.1148/radiol.2020201620.
Epub 2020 Sep 8. PMID: 32897160.
[3] Richardson LC,
Henley SJ, Miller JW, Massetti G, Thomas CC. Patterns and Trends in
Age-Specific Black-White Differences in Breast Cancer Incidence and Mortality –
United States, 1999–2014. MMWR Morb Mortal Wkly Rep 2016;65:1093–1098. DOI:
http://dx.doi.org/10.15585/mmwr.mm6540a1external icon.
[4] Siddharth S, Sharma
D. Racial Disparity and Triple-Negative Breast Cancer in African-American
Women: A Multifaceted Affair between Obesity, Biology, and Socioeconomic
Determinants. Cancers (Basel). 2018;10(12):514. Published 2018 Dec 14.
doi:10.3390/cancers10120514
[5] American Cancer
Society. Inflammatory Breast Cancer. https://www.cancer.org/cancer/breast-cancer/about/types-of-breast-cancer/inflammatory-breast-cancer.html#:~:text=IBC%20tends%20to%20occur%20in,common%20types%20of%20breast%20cancer.
[6] Marmot M, Altman G,
Cameron A, et al. The benefits and harms
of breast cancer screening: an independent review. Br J Cancer. 2013;108(11):2205-2240.
[7] NIH National Cancer
Institute. Mammograms Fact Sheet. Accessed via
https://www.cancer.gov/types/breast/mammograms-fact-sheet.
[8] Lauby-Secretan B,
Scoccianti C, Loomis D et al.; Breast-cancer screening–viewpoint of the IARC
Working Group; N Engl J Med. 2015 Jun 11;372(24):2353-8. doi:
10.1056/NEJMsr1504363.
[9] Irvin VL, Zhang Z, Simon MS, et al. Comparison of Mortality Among Participants of
Women’s Health Initiative Trials With Screening-Detected Breast Cancers vs
Interval Breast Cancers. JAMA Netw Open. 2020;3(6):e207227. Published 2020 Jun
1. doi:10.1001/jamanetworkopen.2020.7227
[10] U.S. Breast Cancer
Statistics. Breastcancer.org. Accessed via https://www.breastcancer.org/symptoms/understand_bc/statistics.