AI-Based Technology for Ultrasound Image Analysis Receives FDA Approval
By MedImaging International staff writers Posted on 17 Jul 2019 |

Image: A screenshot of the Koios DS Breast 2.0 AI-based software (Photo courtesy of Koios Medical).
Koios Medical, Inc (Chicago, IL, USA), a developer of ultrasound diagnosis decision support software, has received 510(k) clearance from the US 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.
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. The patented software uses an ensemble of algorithms to aid the early detection of disease while also reducing biopsies of benign tissue. Koios DS Breast 2.0 can be used in conjunction with most major PACS platforms and is directly available on the LOGIQ 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.
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,” said Koios Medical CEO Chad McClennan. “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.”
Related Links:
Koios Medical
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. The patented software uses an ensemble of algorithms to aid the early detection of disease while also reducing biopsies of benign tissue. Koios DS Breast 2.0 can be used in conjunction with most major PACS platforms and is directly available on the LOGIQ 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.
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,” said Koios Medical CEO Chad McClennan. “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.”
Related Links:
Koios Medical
Latest Imaging IT News
- New Google Cloud Medical Imaging Suite Makes Imaging Healthcare Data More Accessible
- Global AI in Medical Diagnostics Market to Be Driven by Demand for Image Recognition in Radiology
- AI-Based Mammography Triage Software Helps Dramatically Improve Interpretation Process
- Artificial Intelligence (AI) Program Accurately Predicts Lung Cancer Risk from CT Images
- Image Management Platform Streamlines Treatment Plans
- AI Technology for Detecting Breast Cancer Receives CE Mark Approval
- Digital Pathology Software Improves Workflow Efficiency
- Patient-Centric Portal Facilitates Direct Imaging Access
- New Workstation Supports Customer-Driven Imaging Workflow
Channels
Radiography
view channel
AI-Powered Mammography Screening Boosts Cancer Detection in Single-Reader Settings
A new study has revealed that an artificial intelligence (AI)-powered solution significantly improves cancer detection in single-reader mammography settings without increasing recall rates, offering a... Read more
Photon Counting Detectors Promise Fast Color X-Ray Images
For many years, healthcare professionals have depended on traditional 2D X-rays to diagnose common bone fractures, though small fractures or soft tissue damage, such as cancers, can often be missed.... Read moreMRI
view channel
Biparametric MRI Combined with AI Enhances Detection of Clinically Significant Prostate Cancer
Artificial intelligence (AI) technologies are transforming the way medical images are analyzed, offering unprecedented capabilities in quantitatively extracting features that go beyond traditional visual... Read more
First-Of-Its-Kind AI-Driven Brain Imaging Platform to Better Guide Stroke Treatment Options
Each year, approximately 800,000 people in the U.S. experience strokes, with marginalized and minoritized groups being disproportionately affected. Strokes vary in terms of size and location within the... Read moreUltrasound
view channel
Artificial Intelligence Detects Undiagnosed Liver Disease from Echocardiograms
Echocardiography is a diagnostic procedure that uses ultrasound to visualize the heart and its associated structures. This imaging test is commonly used as an early screening method when doctors suspect... Read more
Ultrasound Imaging Non-Invasively Tracks Tumor Response to Radiation and Immunotherapy
While immunotherapy holds promise in the fight against triple-negative breast cancer, many patients fail to respond to current treatments. A major challenge has been predicting and monitoring how individual... Read moreNuclear Medicine
view channel
Novel Radiotracer Identifies Biomarker for Triple-Negative Breast Cancer
Triple-negative breast cancer (TNBC), which represents 15-20% of all breast cancer cases, is one of the most aggressive subtypes, with a five-year survival rate of about 40%. Due to its significant heterogeneity... Read more
Innovative PET Imaging Technique to Help Diagnose Neurodegeneration
Neurodegenerative diseases, such as amyotrophic lateral sclerosis (ALS) and Alzheimer’s disease, are often diagnosed only after physical symptoms appear, by which time treatment may no longer be effective.... Read moreGeneral/Advanced Imaging
view channel
AI Reduces CT Lung Cancer Screening Workload by Almost 80%
Lung cancer impacts over 48,000 individuals in the UK annually, and early detection is key to improving survival rates. The UK Lung Cancer Screening (UKLS) trial has already shown that low-dose CT (LDCT)... Read more
Cutting-Edge Technology Combines Light and Sound for Real-Time Stroke Monitoring
Stroke is the second leading cause of death globally, claiming millions of lives each year. Ischemic stroke, in particular, occurs when a blood vessel that supplies blood to the brain becomes blocked.... Read more
AI System Detects Subtle Changes in Series of Medical Images Over Time
Traditional approaches for analyzing longitudinal image datasets typically require significant customization and extensive pre-processing. For instance, in studies of the brain, researchers often begin... Read more
New CT Scan Technique to Improve Prognosis and Treatments for Head and Neck Cancers
Cancers of the mouth, nose, and throat are becoming increasingly common in the U.S., particularly among younger individuals. Approximately 60,000 new cases are diagnosed annually, with 20% of these cases... Read moreIndustry News
view channel
Siemens and Sectra Collaborate on Enhancing Radiology Workflows
Siemens Healthineers (Forchheim, Germany) and Sectra (Linköping, Sweden) have entered into a collaboration aimed at enhancing radiologists' diagnostic capabilities and, in turn, improving patient care... Read more