New Research Indicates ProFound AI May Reduce Interval Breast Cancer Rates

Rhea-AI Summary

iCAD announced a retrospective analysis published in the Journal of Medical Screening showing that its ProFound AI for 2D Mammography could detect 48% of interval cancers, including 93% of false negatives and minimal sign lesions. The study involved 37,367 women screened between 2011 and 2012, identifying various categories of interval cancers. This could enhance breast cancer detection rates in organized screening programs, ultimately leading to earlier treatment and improved outcomes for women.

Positive

• ProFound AI detected 93% of interval cancers with minimal signs and false negatives.
• Potential to reduce interval cancer rates and enhance early detection.
• Analysis supports the effectiveness of AI in improving mammography screening results.

Negative

• None.

Retrospective analysis published in Journal of Medical Screening suggests that ProFound AI for 2D Mammography could have helped detect 48% of interval cancers and 93% of subgroups that include false-negatives and minimal sign lesions

NASHUA, N.H., March 31, 2021 (GLOBE NEWSWIRE) -- iCAD, Inc. (NASDAQ: ICAD), a global medical technology leader providing innovative cancer detection and therapy solutions, today announced that ProFound^® AI for 2D Mammography might notably reduce the risk of interval breast cancer, according to a retrospective analysis recently published in the Journal of Medical Screening.¹

The aim of the study was to determine if adding AI to reading mammography as a supportive tool may help in decreasing the interval cancer rate in population-based organized mammography screening programs in Germany.

“Interval breast cancers—cancers that are diagnosed after a negative mammography screening, but before the next recommended screening exam, can be linked to a poor prognosis such as cancer that has already spread, or a more aggressive type of cancer, thus underscoring the need for iCAD’s deep-learning algorithm that can analyze each mammography image and provide critical insight into individual cases,” said Michael Klein, Chairman and CEO of iCAD. “The data from this retrospective analysis are very encouraging in Europe while also having an impact on screening in the US. The results further stress the importance of our ProFound AI platform as a world-class artificial intelligence (AI) solution offering benefits to radiologists and women in improving breast cancer detection rates, reducing false positives and unnecessary callbacks, and providing more personalized screening for every woman.”

In the retrospective analysis, which evaluated a screening period from 2011 and 2012, a total of 37,367 women between the ages of 50-69 were screened with full-field digital mammography (FFDM). Of these, 29 cases of interval cancers with full documentation were evaluated using ProFound AI for 2D Mammography. For quality assurance, interval cancers with the prior screening mammogram were classified in four categories by the radiologists: true interval cancers, minimal sign cancers, missed cancers (false negative) based on the original screening exam deemed as normal and dismissed, and occult cancers. The objective of the study was to determine whether ProFound AI for 2D Mammography could identify interval cancers that had either minimal signs in the original normal screening or were missed in the original screening round where they had been dismissed as a normal exam.

According to the lead author of the study, Axel Gräwingholt, MD, Radiologie am Theater in Paderborn, Germany, “The results indicate that ProFound AI for 2D Mammography found 93% of these cancers—eight out of nine cancers that presented minimal signs and six out of six that were false negatives, or missed in the screening round—demonstrating that some cancers could have been detected earlier within the screening round where they were dismissed as normal and therefore wouldn’t have been detected as interval cancers.”

“As a result, ProFound AI as a clinical tool for radiologists has the potential to reduce interval cancer rates by detecting cancers that are already present in the screening round but are perhaps undetected or missed by the readers,” continued Dr. Gräwingholt. “Using this technology at the screening level could limit the number of false negatives and help to detect a large proportion of the minimal sign cancers, which could ensure earlier treatment and better chances of recovery for these women.”

“This study contributes to the growing body of evidence that demonstrates the clear value ProFound AI for 2D Mammography can offer to screening programs across Europe, benefiting both the patient and the clinician,” said Michele Debain, Vice President of Europe, Middle East and Africa at iCAD. “It is essential to detect breast cancers as early as possible, as the cancer can grow, develop and spread. Earlier cancer detection allows for earlier treatment, which in turn could lead to less stress for the patient and lower costs for the national health systems. In addition, the rate of interval cancers is typically used as a measure for the quality of the national mammography screening program.”

iCAD’s Breast Health Solutions suite includes ProFound AI for Digital Breast Tomosynthesis (DBT) and software solutions for 2D mammography, risk evaluation and breast density. In 2018, ProFound AI for DBT received its CE mark, Health Canada approval and was the first 3D tomosynthesis software using AI to receive clearance from the U.S. Food and Drug Administration (FDA). ProFound AI for 2D Mammography received a CE mark in July 2019. In a reader study published in Radiology, ProFound AI for DBT was shown to offer clinically proven time-savings benefits to radiologists, reducing reading time by 52.7 percent, improving radiologist sensitivity by 8 percent, and reducing false positives and unnecessary patient recall rates by 7.2 percent.²

Dr. Axel Gräwingholt’s Biography

Dr. Axel Gräwingholt is a radiologist specializing in breast imaging. He is a co-owner of a private radiology institute in Germany with a screening unit for the German official breast cancer screening program, and he is also involved in several screening programs in Europe as a reader (Germany, Switzerland, Norway). Dr. Gräwingholt also participated in the TOSYMA trial in Germany to assess the value of tomosynthesis in organized screening programs. He is clinical co-chair of the European guidelines for breast cancer (ECIBC), and he is a lecturer on courses about mammography and tomosynthesis screening in different countries, including Switzerland, Armenia, China and Greece.

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 and www.xoftinc.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 benefits of the Company’s agreement with Solis 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. 

Contacts:
Media inquiries USA:
Jessica Burns, iCAD
+1-201-423-4492
jburns@icadmed.com

Media inquiries Europe:
Emmanuelle Vella, iCAD
+33 620 49 48 57
evella@icadmed.com

Investor Relations:
Jeremy Feffer, LifeSci Advisors
+1-212-915-2568
jeremy@lifesciadvisors.com

¹ Graewingholt A, Rossi PG. (2021). Retrospective analysis of the effect on interval cancer rate of adding an artificial intelligence algorithm to the reading process for two-dimensional full-field digital mammography. J Med Screen. 0(0) 1-3.
Accessed via https://journals.sagepub.com/doi/10.1177/0969141320988049
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