November 28, 2023 — iCAD, Inc., a global medical technology company developing cancer-detection solutions, will present new studies validating its artificial intelligence (AI) powered ProFound Breast Health Suite for uncovering hidden heart or vascular disease, and predicting a woman’s risk for developing breast cancer in the next one- or two-years. Researchers will present their findings at the Radiological Society of North America’s Annual Meeting, RSNA 2023, in Chicago, Nov. 26–30, 2023.
Blending artificial intelligence with computer-aided detection (AI CAD), the iCAD software platform, ProFound Breast Health Suite, can screen a single mammogram for two of the top causes of death for women: breast cancer and heart disease. ProFound AI improves accuracy, streamlines clinical workflow and delivers results to patients more quickly.
“The ProFound Breast Health Suite significantly increases cancer detection rates with up to 2x enhanced clinical performance compared to other AI platforms, and reduces the rate of false positive results while accurately evaluating a woman’s breast density and cancer risk,” said Dana Brown, president and CEO of iCAD, Inc. “Our growing body of important research illustrates the potential our newest solution, ProFound Heart Health, holds for the assessment of calcium deposits in the breast arteries as a proxy for hidden cardiovascular disease, the leading cause of death for women worldwide. We believe iCAD’s ProFound AI has the power to positively transform healthcare for clinicians and patients alike.”
Catching cardiovascular disease through mammography
Recent research shows that calcium deposits inside the blood vessels of the breast correlate to hardening of the cardiovascular arteries. In fact, women with breast arterial calcifications, or BAC, are 51% more likely to develop heart disease. iCAD's report on the existence of arterial calcification, along with easy-to-understand visual representations that demonstrate the extent of calcification, can help women work with their physicians to further evaluate their cardiovascular health and identify any potential need for intervention.
Chirag Parghi, M.D., chief medical officer of Solis Mammography, and a pioneer in the use of mammography to assess BAC, will present his team’s findings from a 15-site prospective study that reviewed 2D screening mammograms from 15,785 asymptomatic women, ages 20 to 97. He and his colleagues found the ProFound Heart Health AI algorithm highly accurate in uncovering BAC in mammograms. The calcium deposits appeared more common and widespread with age, as expected.
“Radiologists currently rely on visual detection of breast arterial calcifications, which is time-consuming and leads to a national underreporting of BAC results in mammography reports,” explained Dr. Parghi. “Our study suggests that AI can standardize BAC detection on a large scale, speeding up the measurement process and reducing variations between reviewers. By standardizing BAC reporting, AI increases the ease of identifying women that may benefit from additional cardiovascular screening.” Dr. Parghi’s oral presentation will occur on Tuesday, Nov. 28, 9:30 - 10:30 am CST: “AI Assessment of Breast Arterial Calcifications on Mammography in a Large Screening Population” (Session T3-SSBR05).
Accurately predicting personal breast cancer risk
Axel Gräwingholt, M.D., head of mammography screening at Radiologie am Theater in Germany, will present his team’s findings from a retrospective study of ProFound Risk for 2D Mammography. He and his colleagues assessed ProFound Risk’s effectiveness in identifying women at high risk for developing breast cancer in the next two years based on microscopic changes on their exams.
The researchers used ProFound Risk to screen the mammograms of 53,453 women who had received normal results two years earlier from their radiologists. The program flagged 42.8% of the women, or 22,878 patients, at a higher risk for breast cancer.
ProFound Risk’s prediction proved correct. The average risk for women in the study who developed breast cancer two years after their mammogram was 2.4 times higher than for those who remained cancer-free. The average risk for invasive cancers exceeded that of ductal carcinoma in situ (DCIS), a slow-growing cancer of the milk ducts.
“Our findings suggest AI enables radiologists to identify women who would benefit from more frequent screenings, or suggest supplemental screenings, without leading to overdiagnosis,” said Dr. Gräwingholt. “ProFound Risk accurately pinpoints women at high risk for breast cancer while helping us discover small, subtle and aggressive cancers that often go undetected by the naked eye. We believe this technology could greatly enhance the effectiveness of breast cancer screening strategies worldwide.”
Dr. Gräwingholt’s oral presentation will occur on Monday, Nov. 27, 8:00 – 9:00 am CST: “Real-World Use of AI Risk Scores to Identify Women at High Risk for Breast Cancers with Sub-analyses Based on Histopathology and Time of Detection” (Session M1-SSBR03).
Emily Conant, M.D., professor of Radiology and Vice Chair of Faculty Development in the Department of Radiology at the University of Pennsylvania, Perelman School of Medicine, will deliver an Industry Summit presentation, “From Pixels to Practice: Harnessing Innovations in Breast AI to Improve Patient Outcomes.” showcasing promising early testing results from iCAD’s newest 4th generation AI for breast cancer detection Monday, Nov. 27, 3:30 – 3:45 pm CST (AI Showcase Theater)
Thu Ha Dao, M.D., a radiologist at Hôpitaux Universitaires Henri Mondor in France, will deliver a poster presentation on Sunday, Nov. 26 from 12:15 – 12:45 pm CST: “Evaluation of a Deep-learning based Software Tool to Automatically Detect and Quantify Breast Arterial Calcifications in Digital Mammograms.” (Session S3B-SPBR-1)
Mikael Eriksson, Ph.D., a postdoctoral researcher of medical epidemiology and biostatistics at the Karolinska Institute in Sweden, will deliver a poster presentation on Monday, Nov. 27 from 12:45 – 1:15 pm CST: “Multi-national validation of a clinical image-based AI-risk model for individualizing breast cancer screening.” (Session M5B-SPBR-4)
iCAD staff will showcase the ProFound Breast Health Suite in an interactive exhibit for attendees demonstrating how to add and scale AI in their radiology practices. (RSNA South Hall, Booth 3940). Solutions demonstrated include:
ProFound Detection*: both the current cleared breast cancer detection 3.0 version and future 4.0 version (4.0 not yet FDA cleared) will be available to observe for their ability to detect tumors; as well as the newest 2D version developed in collaboration with Google Health (not yet FDA cleared or CE marked).
ProFound Density: a solution for objective, standardized assessments of breast density.
ProFound Risk**: predicting a woman’s one- and two-year risk for developing breast cancer.
ProFound Heart Health***: a new solution for measuring cardiovascular calcium deposits, alerting to possible vascular or heart disease (pending FDA clearance).
iCAD will also host a series of “Meet the Experts” sessions throughout the annual meeting featuring radiology, research, and technology leaders in breast imaging AI who will be available to share their experience with the ProFound Breast Health Suite. To learn more about iCAD’s presence at RSNA or to RSVP for an event, please visit https://web.icadmed.com/RSNA-2023.html
*ProFound Detection version 4.0 and ProFound Detection for 2D in partnership with Google are not yet submitted for FDA clearance or available for sale in the U.S. or CE Marked.
**ProFound Risk is CE Marked, Health Canada Licensed, and available for investigational use only in the U.S.
***ProFound Heart Heath is available for investigational use only, pending regulatory approval in the U.S. and Europe.
For more information: www.icadmed.com
Follow more coverage of RSNA 2023 news and updates here.
April 23, 2024 
