Arterys has received 510(k) clearance from the US Food and Drug Administration (FDA) to market its Arterys Cardio deep learning (DL) application. Arterys Cardio DL leverages cloud computing and deep learning in a clinical setting.
Arterys Cardio DL provides automated, editable ventricle segmentations based on conventional cardiac MRI images that are as accurate as segmentations performed manually by experienced physicians.
Fabien Beckers, Arterys chief executive officer says, “This application demonstrates…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.”
The Arterys Cardio DL application is vendor agnostic and was developed using data from several thousand cardiac cases. The software produces editable automated contours, providing precise and consistent ventricular function in seconds. According to a company release, the trained deep learning algorithm was validated as producing results within an expected error range comparable to that of an experienced clinical annotator.
The FDA clearance enables Arterys to make use of its clinical annotation platform, which collects ground-truth data every time a user views a study on Arterys.com. In the future, the deep learning model can be optimised as new data is collected from all global users.
Arterys received CE mark in late December for commercialisation of the Cardio DL product in Europe.
Both the FDA clearance and CE mark expand on the recently 510(k)-cleared 4D Flow post-processing software features that are designed to provide anatomy and blood flow visualisation and quantification within and around the heart in a simple manner.