FDA Clears Koios DS™ Breast 2.0 to Assist Physicians with AI-Based Software
Koios Medical, Inc has received 510(k) clearance from the U.S. Food and Drug Administration for Koios DS (Decision Support) Breast 2.0, a new version of its machine learning based platform that assists physicians in the classification and diagnosis of breast cancer.
The software offers a proprietary alignment to BI-RADS® for any lesion analyzed and is available connected to PACS and/or directly on GE Healthcare's LOGIQ™ E10 ultrasound system.
CHICAGO, July 9, 2019 /PRNewswire/ -- Koios Medical, the leader in ultrasound diagnosis decision support software, announces its second 510(k) clearance from the U.S. Food and Drug Administration (FDA).
Koios DS (Decision Support) Breast 2.0 is intended for use to assist physicians analyzing breast ultrasound images and aligns a machine learning generated probability of malignancy with the appropriate BI-RADS category.
This milestone is an important step in advancing the company's mission of empowering physicians to improve diagnostic accuracy. Now cleared for use at the point of care (or connected to an image viewer for studies stored on PACS), Koios Medical's advancements represent a huge leap forward in using artificial intelligence in healthcare by bringing the power of deep learning to physicians' fingertips. Koios DS Breast 2.0 represents the most advanced AI-based diagnostic technology for ultrasound image analysis to date. This patented software uses an ensemble of algorithms to aid the early detection of disease while also reducing biopsies of benign tissue.
In a recent reader study involving 15 physicians with relevant experience up to 39 years, each randomly analyzed 900 cases twice, separated by a one-month "washout period." Physicians utilizing the Koios DS 2.0 AI software experienced a statistically significant improvement in accuracy as measured by area under the ROC (receiver operating characteristic) curve (AUC), while simultaneously reducing both inter and intra-operator variability.
"We are seeing the promise of machine learning as a physician's assistant coming to fruition. This will undoubtedly improve quality, outcomes, and patient experiences—and ultimately save lives. Koios DS Breast 2.0 is proving that a system trained by hundreds of thousands of images linked to their ground truth can catch many more cancers earlier, while simultaneously reducing benign biopsies and all the anxiety, complications, and associated expense. Smart ultrasound is a second set of eyes that achieves what was previously unthinkable," says Koios Medical CEO Chad McClennan.
Koios DS Breast 2.0 can be used in conjunction with most major PACS platforms and is directly available on the LOGIQTM E10, GE Healthcare's next generation digital ultrasound system that integrates artificial intelligence, cloud connectivity, and advanced algorithms to acquire and reconstruct data. Machine generated results can be exported directly into a patient's record. Koios Medical continues to experiment with thyroid ultrasound image data and expects to add to its offering later this year.
About Koios Medical:
Koios Medical develops medical software to assist physicians interpreting ultrasound images and applies deep learning methods to the process of reaching an accurate diagnosis. The Koios DS platform uses advanced algorithms to assist in the early detection of disease while reducing recommendations for biopsy of benign tissue. Patented technology saves physicians time, helps improve patient outcomes, and reduces healthcare costs. Koios DS Breast is presently focused on breast cancer diagnosis assistance market. Women with dense breast tissue (over 40% in the US) often require an alternative to mammography for diagnosis. Ultrasound is a widely available and effective alternative to mammography with no radiation and is standard of care for breast cancer diagnosis. To learn more please contact us at [email protected] or (732) 529-5755.