AI loaded onto mammography systems can flag possible cancers in real time to speed workflows

Patient anxiety from mammography recalls and the need to wait for scheduled follow-up exams or biopsies is an issue many women's imaging centers are trying to avoid. Artificial intelligence (AI) embedded directly in the breast imaging systems might be one way to enable faster care to eliminate the wait and to help speed same-day workflows for additional imaging or biopsies.

MedCognetics Inc. said this week it successfully tested and implemented the first embedded AI cancer detection system built into a mammography system. The embedded solution eliminates latency, delivering immediate, high-quality image analysis, a significant improvement over traditional setups that require external workstations or cloud-based processing. This approach may improve patient outcomes through faster results, enhanced image quality and reduced hardware costs.

The vendor gained U.S. Food and Drug Administration clearance for its CogNet QmTriage AI in September 2022, which can be integrated directly into a full-field digital mammography (FFDM) system and flag exams where there is a suspected cancer. This can enable exams to be flagged for priority reads so patients can get additional screenings or a biopsy while at the imaging center, rather than notifying patients later and requiring them to schedule a different appointment.

The technology implemented this week is the company's upgraded CogNet AI-MT technology, which employs advanced AI and machine learning (ML) to detect early signs of cancer across all ethnicities and can be deployed on customer premises, in the cloud, or via the web. The platform is FDA 510(k) cleared for triage of mammogram images. The system uses the Nvidia IGX Orin medical-grade edge AI platform alongside CogNet AI-MT. The algorithm was trained on a diverse global dataset to enhance the performance of radiologists and help improve patient outcomes worldwide, the company said.

MedCognetics said the AI offers complete analysis in the radiology workflow, on premise, reducing the wait time for results. AI-driven enhancements improve the clarity and detail of images without requiring high-end, expensive hardware. The vendor said it is a cost efficiency solution for medical device manufacturers to achieve high-end image quality at a fraction of the cost by utilizing AI rather than upgrading hardware. The AI cans also help practices with workflow optimization by enabling worklist prioritization.

Dave Fornell is a digital editor with Cardiovascular Business and Radiology Business magazines. He has been covering healthcare for more than 16 years.

Dave Fornell has covered healthcare for more than 17 years, with a focus in cardiology and radiology. Fornell is a 5-time winner of a Jesse H. Neal Award, the most prestigious editorial honors in the field of specialized journalism. The wins included best technical content, best use of social media and best COVID-19 coverage. Fornell was also a three-time Neal finalist for best range of work by a single author. He produces more than 100 editorial videos each year, most of them interviews with key opinion leaders in medicine. He also writes technical articles, covers key trends, conducts video hospital site visits, and is very involved with social media. E-mail: dfornell@innovatehealthcare.com

Around the web

The new technology shows early potential to make a significant impact on imaging workflows and patient care. 

Richard Heller III, MD, RSNA board member and senior VP of policy at Radiology Partners, offers an overview of policies in Congress that are directly impacting imaging.
 

The two companies aim to improve patient access to high-quality MRI scans by combining their artificial intelligence capabilities.