Studies presented at two leading breast imaging conferences demonstrate
ProFound AI
helps radiologists identify normal mammograms and those with increased
likelihood of malignancy with precision
NASHUA, N.H. –
April 19, 2021 – iCAD, Inc. (NASDAQ: ICAD), a
global medical technology leader providing innovative cancer detection and
therapy solutions, today announced that new research supporting the clinical
value of ProFound AI® for Digital
Breast Tomosynthesis (DBT) was presented at the Society of Breast Imaging (SBI) Symposium,
April 9-11, and at the National Consortium of Breast Centers (NCBC) Annual Interdisciplinary
Breast Center Conference (NCoBC), April 16-19.
Emily Conant, MD, Professor and Division Chief of Breast Imaging at the
University of Pennsylvania Medical Center, presented findings from a
retrospective analysis involving ProFound AI for DBT in a presentation titled
“Feasibility of automated identification of low-likelihood of cancer cases in
digital breast tomosynthesis screening,” at the SBI Symposium. At the NCoBC
Interdisciplinary Breast Center Conference, Mark Traill, MD, University of
Michigan Health, presented findings from a study titled “Correlation between
BI-RADS Assessment Categories and Artificial Intelligence Case Scores,” which
was a winner in the “Breast Disease Diagnosis and Management” category.
“These two studies both suggest that ProFound AI Case Scores
provide valuable insights that can help clinicians more efficiently identify normal
mammograms, which may directly translate to time-savings benefits,” said
Michael Klein, Chairman and CEO of iCAD. “In addition, ProFound AI is
clinically proven to improve radiologists’ sensitivity while simultaneously
improving their specificity, which is a huge performance achievement in breast
care. With the addition of these two important abstracts, research now shows
how Case Scores can be used in the clinical setting to help radiologists feel
more confident in their decisions about when a mammogram is normal.”
According to study findings presented by Dr. Conant at the SBI Symposium,
ProFound AI for DBT accurately identified 33.4 percent of normal screening DBT
exams with no cancers being missed, based solely on the ProFound AI Case Score.
When researchers also factored in breast density and age, ProFound AI
identified 58.6 percent of normal cases with no false negatives.
“Our retrospective study demonstrates the feasibility that clinical
algorithms have the potential to triage and reduce screening DBT workload by
flagging normal mammograms using an AI system, and also prioritizing complex
cases that are more likely to require additional review or evaluation,” said
Dr. Conant. “We are pleased to have our research add to the important growing
body of evidence supporting the significance and value of AI in breast
screening.”
The study was conducted to evaluate the thresholds at which the ProFound
AI system could be used for triaging DBT exams to reach a minimum rate of false negatives per 1,000
screened in an enriched dataset of 506 biopsy-proven cancer cases and 1,293
non-cancer cases with 320 days of negative follow-up. A consecutive series of cases
were collected from 18 sites in the United States and three sites in France.
In addition, new data presented by Dr. Mark Traill at the NCoBC Interdisciplinary
Breast Center Conference highlights the comparison of ProFound AI Case Scores to
BI-RADS assessment categories determined by a single radiologist without using
AI in a retrospective analysis. Researchers used ProFound AI on 890 consecutive
DBT studies and 50 consecutive cases with biopsy-proven breast cancer detected
with DBT. Results showed a strong positive correlation between a ProFound
AI Case Score of less than 60 percent and
patients assessed as likely to be normal (BI-RADS 1 or 2), while most of the
biopsy-proven cancers had a Case Score of greater than 60 percent.
“We wanted to describe
the Case Score distribution in a screening population to better understand the
significance of score value as a clinical decision tool,” said Dr. Traill. “We
found a very strong correlation between a Case Score of less than 60 percent
and a BI-RADS score assessment of 1 or 2. Also, only 15 percent of the Case Scores
were greater than 60 percent, but this group contained most of the detected
cancers. As a clinical decision tool, a Case Score above 60 percent is an
independent indicator of higher chance of underlying malignancy. This is very
helpful in guiding the intensity of the cancer search, while improving workflow
functionality and reducing stress for the reading radiologist.”
ProFound AI for DBT is a high-performance, deep-learning
workflow solution trained to detect malignant soft-tissue densities and
calcifications. It became the first 3D tomosynthesis software using artificial
intelligence (AI) to be FDA cleared in December 2018. Built with the latest in deep-learning
technology, ProFound AI for DBT rapidly analyzes each tomosynthesis image,
detecting malignant soft tissue densities. Certainty of Finding and Case Scores are relative scores
computed by the ProFound AI algorithm and represent its confidence that a
detection or case is malignant. The Certainty of Finding scores help
radiologists by aiding in clinical decision making. Case Scores, which are
assigned to each case by the algorithm, help clinicians to gain a sense of case
complexity, which may be useful for prioritizing the reading worklist. In a reader study published in Radiology: Artificial
Intelligence,
ProFound AI for DBT Version 2.0 was clinically proven to reduce reading time for
radiologists by 52.7 percent, improve radiologists’ sensitivity by 8 percent,
and reduce the rate of false positives and unnecessary patient recalls by 7.2
percent.[1]
The latest version of ProFound AI for
DBT, version 3.0, was recently cleared by the FDA in March 2021. Compared to
previous versions of the software, the ProFound AI 3.0 algorithm offers up to an
additional 10 percent improvement in specificity performance and up to an
additional 1 percent improvement in sensitivity over its previous deep-learning
AI software generation (ProFound AI Version 2.1).[2] ProFound AI version 3.0 also offers up to 40 percent faster
processing on the new PowerLook platform.2 ProFound AI version
3.0 was developed using over five million images from 30,000 cases, including
almost 8,000 biopsy-proven cancers, and validated on approximately one million
images from 3,500 cases that included 1,200 biopsy-proven cancers.
iCAD’s Breast Health Solutions suite also includes software to evaluate breast density, ProFound AI
for 2D Mammography, and ProFound AI Risk, the world’s first and only clinical
decision support tool that provides an accurate two-year breast cancer risk
estimation that is truly personalized for each woman, based only on a screening
mammogram.[3]
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 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:
Jessica Burns, iCAD
+1-201-423-4492
Investor Relations:
Jeremy Feffer,
LifeSci Advisors
+1-212-915-2568
[1] 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
[2] iCAD data on file. Standalone
performance varies by vendor. FDA Cleared.
[3] Eriksson M, Czene K, Strand F, 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