New and Real-World Clinical Evidence Confirms ProFound AI Increases Cancer Detection without Increasing the Rate of Recalls and Reveals Critical Clues to Inform Clinical Decisions
iCAD’s ProFound AI has shown promising results in increasing breast cancer detection rates according to new research presented at the American Roentgen Ray Society (ARRS) meeting. The studies revealed that ProFound AI enhanced radiologists' accuracy without increasing abnormal interpretation or recall rates. One study from the University of Florida demonstrated improved performance among radiologists using ProFound AI, highlighting its capability to provide vital clues for clinical decisions through lesion and case scores. These scores, ranging from 0-100, offer insights into malignancy likelihood, supporting personalized patient care. With over 7,500 installations globally, ProFound AI’s early adoption since its FDA clearance in 2018 has led to significant improvements in detection accuracy and reduced unnecessary callbacks.
- ProFound AI increased cancer detection rates without raising recall rates.
- The product has been validated by leading facilities and research institutions.
- ProFound AI was proven to improve radiologists' sensitivity by 8% in a large study.
- With over 7,500 installations globally, the technology is now the most widely used in its category.
- None.
New research presented at American Roentgen Ray Society (ARRS) meeting continues to validate unique value iCAD’s deep-learning breast AI solution offers to clinicians and patients
NASHUA, N.H., April 20, 2023 (GLOBE NEWSWIRE) -- iCAD, Inc. (NASDAQ: ICAD), a global medical technology leader providing innovative cancer detection and therapy solutions, today announced new real-world research confirms ProFound AI® has been proven to increase cancer detection rates and provide vital clues for breast imagers' clinical decisions through two studies. One study demonstrated that ProFound AI improved radiologists' performance in detecting breast cancer and providing better accuracy, without increasing abnormal interpretation rates or the rate of recalls. The second study highlighted that the lesion and Case Scores provided by ProFound AI offer important information about the algorithm's confidence in identifying malignancy, with sequential changes in these scores offering significant additional insights. These studies were presented at the American Roentgen Ray Society (ARRS) meeting, which took place April 16-20 in Honolulu, HI.
“The body of evidence supporting our Breast AI Suite grows as leading facilities and academic institutions worldwide continue to validate the unmatched results and benefits our technologies offer,” said Dana Brown, President and CEO of iCAD, Inc. “The studies presented at the ARRS meeting confirm that ProFound AI not only improves radiologists’ performance and aids in the detection of breast cancer, but also reveals valuable clues over time through Case Scores, which can help clinicians make more informed clinical decisions and personalize patient care.”
Real-world study confirms iCAD’s AI increases cancer detection, without increasing recalls
In a scientific poster presentation titled “Effect of Artificial Intelligence Software on Digital Breast Tomosynthesis Screening Cancer Detection, Abnormal Interpretation Rates, and Positive Predictive Value Among Subspecialized Breast Radiologists: Cumulative Real-World Evidence,” researchers at the University of Florida-Jacksonville, FL examined the performance of five breast imaging radiologists for one year at a site with iCAD’s ProFound AI compared with the performance of the same five radiologists during the same year at two sites that did not have ProFound AI. iCAD’s ProFound AI increased cancer detection rates and positive predictive value for cancer among abnormal interpretations (PPV1), without increasing abnormal interpretation rates across the radiologists studied. Researchers concluded ProFound AI resulted in clinically relevant increases in cancer detection, without increasing the rate of recalls.
“As digital breast tomosynthesis (DBT) becomes the standard of care for screening mammography, radiologists are facing an exponential increase in the amount of data they are tasked with interpreting each day. We were curious to learn if ProFound AI could help us read DBT with greater accuracy after a year of use,” said the study’s lead author, Haley Letter, M.D. “This real-world evidence confirms ProFound AI can increase cancer detection and improve accuracy in a clinical setting.”
“ProFound AI acts as another pair of eyes that alerts our team to areas that may need further evaluation, while also helping us to avoid calling women back unnecessarily, which can cause a lot of stress for women,” said another researcher on the study, Hector Diaz de Vellegas, D.O., Assistant Professor and Medical Director, Wildlight, University of Florida-Jacksonville, FL. “By improving accuracy, ProFound AI may also improve screening effectiveness, which can ultimately offer peace of mind to both clinicians and patients alike.”
ProFound AI’s Case Scores provide important clues for clinicians to personalize care
In an educational poster presentation titled “Implications of Change in an AI-Derived Case Score on Sequential Years of Digital Breast Tomosynthesis Screening,” Samantha Zuckerman, M.D., M.B.E., Assistant Professor of Clinical Radiology (Breast Imaging), University of Pennsylvania, will discuss how examining ProFound AI’s lesion and Case Scores over time may provide important clues that can help inform clinical decisions. ProFound AI generates a lesion score and a Case Score on a scale of 0-100. The higher the lesion score or Case Score, the more certain the algorithm is that the abnormality could represent a malignancy. Analyzing changes of ProFound AI lesion and Case Scores over sequential rounds of screening and correlating to key clinical outcomes of screening with example true positive (TP), true negative (TN), false positive (FP) and false negative (FN) cases, researchers concluded ProFound AI may alert radiologists to both the location of specific, suspicious lesions, as well as the case-level likelihood of malignancy. Additionally, researchers found an increase in case level and/or lesion level score over sequential screens may also aid radiologists in the detection of screen-detected cancers and identify patients at higher risk for developing breast cancer.
“ProFound AI’s lesion and Case Scores offer critical information about the algorithm’s confidence regarding whether a lesion or case is malignant, but looking at these scores sequentially offers a wealth of knowledge that could have a significant impact on patient care,” said Dr. Zuckerman. “Our research confirms that significant changes in lesion and Case Scores over time may reveal additional clues to clinicians that may help inform important clinical decisions, such as whether to call a woman back for a biopsy or additional imaging.”
Built with the latest in deep-learning AI, ProFound AI became the first AI solution for DBT to be FDA cleared in 2018. With up to two times the improvement in clinical performance compared to leading competitors,1 ProFound AI offers unrivaled accuracy, as well as multi‐vendor compatibility and unique workflow advantages. In a large reader study, iCAD’s ProFound AI was clinically proven to improve radiologists’ sensitivity by
With more than 7,500 licensed installations in more than 20 countries, including some of the world’s largest imaging institutions such as Radiology Partners, SimonMed, and Solis Mammography, iCAD’s breast cancer screening technology is the most widely used technology of its kind.
About iCAD, Inc.
Headquartered in Nashua, NH, iCAD® is a global medical technology leader providing innovative cancer detection and therapy solutions. For more information, visit www.icadmed.com.
Forward-Looking Statements
Certain statements contained in this News Release constitute “forward-looking statements” within the meaning of the Private Securities Litigation Reform Act of 1995, including statements about the expansion of access to the Company’s products, improvement of performance, acceleration of adoption, expected benefits of ProFound AI®, the benefits of the Company’s products, and future prospects for the Company’s technology platforms and products. Such forward-looking statements involve a number of known and unknown risks, uncertainties and other factors which may cause the actual results, performance, or achievements of the Company to be materially different from any future results, performance, or achievements expressed or implied by such forward-looking statements. Such factors include, but are not limited, to the Company’s ability to achieve business and strategic objectives, the willingness of patients to undergo mammography screening in light of risks of potential exposure to Covid-19, whether mammography screening will be treated as an essential procedure, whether ProFound AI will improve reading efficiency, improve specificity and sensitivity, reduce false positives and otherwise prove to be more beneficial for patients and clinicians, the impact of supply and manufacturing constraints or difficulties on our ability to fulfill our orders, uncertainty of future sales levels, to defend itself in litigation matters, protection of patents and other proprietary rights, product market acceptance, possible technological obsolescence of products, increased competition, government regulation, changes in Medicare or other reimbursement policies, risks relating to our existing and future debt obligations, competitive factors, the effects of a decline in the economy or markets served by the Company; and other risks detailed in the Company’s filings with the Securities and Exchange Commission. The words “believe,” “demonstrate,” “intend,” “expect,” “estimate,” “will,” “continue,” “anticipate,” “likely,” “seek,” and similar expressions identify forward-looking statements. Readers are cautioned not to place undue reliance on those forward-looking statements, which speak only as of the date the statement was made. The Company is under no obligation to provide any updates to any information contained in this release. For additional disclosure regarding these and other risks faced by iCAD, please see the disclosure contained in our public filings with the Securities and Exchange Commission, available on the Investors section of our website at http://www.icadmed.com and on the SEC’s website at http://www.sec.gov.
Contact:
Media Inquiries:
Jessica Burns, iCAD
+1-201-423-4492
jburns@icadmed.com
Investor Inquiries:
iCAD Investor Relations
ir@icadmed.com
1 https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm. Accessed 1-19-22. FDA 510K submissions K182373, K201019, K193229
2 Conant, E et al. (2019). Improving Accuracy and Efficiency with Concurrent Use of Artificial Intelligence for Digital Breast Tomosynthesis. Radiology: Artificial Intelligence. 1 (4). Accessed via https://pubs.rsna.org/doi/10.1148/ryai.2019180096
FAQ
What are the key findings of the recent iCAD ProFound AI studies presented at the ARRS meeting?
What benefits does ProFound AI provide to clinicians and patients?
How many installations of ProFound AI are there globally?
What is the significance of the lesion and case scores generated by ProFound AI?
When was ProFound AI first cleared by the FDA?
