August 15, 2023 — iCAD, Inc., a global medical technology leader providing innovative cancer detection and therapy solutions, today announced it signed an amendment to its development and commercialization agreement with Google Health, which will enable iCAD to integrate Google’s AI technology with its ProFound Breast Health Suite for 2D Mammography for use worldwide upon regulatory approval as an independent reader for breast cancer screening for 20 years.
“The conventional double-reading workflow utilized by most countries, where mammograms are assessed by two separate radiologists, has become increasingly challenging due to the scarcity of radiologists worldwide. As the global radiologist shortage continues to impact patient care, healthcare organizations are seeking clinically-proven solutions to help their radiology departments run more efficiently and adeptly handle the workload in front of them. By leveraging the remarkable capabilities of ProFound Detection, iCAD seeks to provide a viable alternative to the current double-reading workflow,” said Dana Brown, President and CEO of iCAD, Inc.
ProFound Detection is a high-performance, deep learning cancer detection solution that is clinically proven to improve detection and workflow efficiency for radiologists reading mammography. Available for both 2D and 3D mammography, it rapidly and accurately analyzes each mammography image, and alerts radiologists of suspicious areas that may warrant a closer look. A growing body of evidence confirms ProFound Detection improves accuracy and efficiency for radiologists, empowering them to find more cancers while reducing the rate of false positives and unnecessary recalls.[i],[ii]
iCAD signed a strategic development and commercialization agreement with Google Health in November 2022 to integrate Google’s AI technology into iCAD’s leading-edge portfolio of breast imaging AI solutions, including ProFound Detection.
“Combining Google’s artificial intelligence (AI) technology with our leading-edge ProFound Breast Health Suite of AI solutions will enhance our technology and expand access to the technology to millions of women and providers worldwide,” added Ms. Brown. “Furthermore, Google has already been exploring the use of its technology as an independent reader, with extremely promising results.”
In an independent study of six radiologists, Google’s mammography AI system outperformed all of the human readers, with an area under the receiver operating characteristic curve (AUC-ROC) that was greater than the AUC-ROC for the average radiologist by an absolute margin of 11.5%. Researchers also ran a simulation in which Google’s AI system participated in the double-reading process used in the UK and found the AI system maintained non-inferior performance and reduced the workload of the second reader by 88%.[iii]
“Technology can and should play a fundamental role in democratizing access to high-quality healthcare. But one company can’t make this a reality alone,” said Greg Corrado, Ph.D., Head of Health AI, Google. “iCAD is a proven leader in the breast cancer domain, and through this collaboration we hope to not only alleviate the increasing burdens on radiologists worldwide, but also reduce disparities in healthcare across the globe.”
“At iCAD, we believe where one lives should not determine whether one lives. As part of our agreement with Google, and to demonstrate our commitment to enhancing patient outcomes worldwide, iCAD will provide a portion of its breast cancer screening for underserved individuals in certain countries at no cost,” added Ms. Brown. “With thousands of installations worldwide, our Breast AI solutions are already the most widely used technologies of their kind. Our solutions level the playing field and provide a more holistic view of each woman’s present and future, optimizing every patient’s opportunity to find cancers earlier and live better lives.”
For more information: www.icadmed.com
[i] 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.
[ii] 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
[iii] McKinney, S.M., Sieniek, M., Godbole, V. et al. International evaluation of an AI system for breast cancer screening. Nature 577, 89–94 (2020). https://doi.org/10.1038/s41586-019-1799-6