Arterys nabs second FDA OK for deep learning, image analysis software

Arterys, which is bringing deep learning to medical image analysis, earned FDA clearance for its software that provides automated ventricle segmentations from conventional heart MRI scans that are as accurate as manual segmentations performed by physicians, the company announced Monday.

The Arterys Cardio DL software automates time-consuming analyses of cardiac MRI images, generating editable contours showing the inside and outside of the ventricles of the heart. The software processes a scan in 10 seconds, far more quickly than a clinician would. The application uses a deep learning algorithm that was trained using data from several thousand cardiac cases, the company said in a statement. The algorithm produces results comparable to those of an experienced clinical annotator, Arterys said.

The FDA clearance and CE mark earned last month allow the software to be used in clinical settings, where it will collect more data in the cloud as more and more physicians use it.

"Arterys is committed to broadly accelerate the transformation of data-driven medicine through advanced cloud medical imaging analytics applications while always protecting patient data privacy," said CEO Fabien Beckers in the statement. "Today's approval signifies a major regulatory milestone. This application demonstrates the power of deep learning combined with cloud supercomputation to aid physicians in interpreting medical images—eliminating tedious manual tasks carried out on a workstation by accurately automating those processes."

In November, the company picked up an FDA nod for its 4D Flow software, which accelerates cardiac examinations by providing clinicians with visualization and quantification of anatomy and blood flow in and around the heart. The software analyzes blood flow to the heart and its major vessels, which can help physicians dealing with cardiac patients make treatment decisions.

Arterys is working with GE to launch its deep learning image analysis system as part of the latter's ViosWorks platform.