AI-Enhanced Cardiac MRI Platform Evaluates Congenital Heart Disease in Real Time

By MedImaging International staff writers
Posted on 08 Apr 2022

Image: New modules have been added to Cardio AI clinical application (Photo courtesy of Arterys)

A comprehensive, cloud-based post-processing solution leverages AI and deep learning to provide extremely accurate, automated, fast, repeatable analysis of cardiac MRI images that are as accurate as segmentations performed manually by expert physicians.

Arterys’ (San Francisco, CA, USA) Cardio AI quantifies and visualizes 4D flow in minutes, enabling physicians to decrease scan time by ~30% and to maintain reimbursements, thus increasing the cost-effectiveness and ROI. By incorporating AI across the cardiac MR workflow, Cardio AI provides physicians with fast access to automated and quantitative cardiac MR image analysis and customizable reporting that reduces tedious and operator-dependent manual tasks, and saves up to 25 minutes per study.

Through the use of deep learning, Cardio AI provides automated, editable ventricular segmentations based on cine cardiac MRI images that are as accurate as segmentations performed manually by expert physicians. Cardio AI does not require on-premises hardware and results are accessible from anywhere and any device through a single user-interface zero footprint viewer and an internet connection. It seamlessly integrates with Powerscribe or Fluency dictation software ensuring exams are read accordingly and consistently.

Arterys has now announced several new modules to its Cardio AI clinical application and an additional FDA AI clearance based on deep learning. The latest Cardio AI enhancements provide physicians with additional tools to remove redundant work and tedious editing to analyze Cardiac MRI images. These new modules make it easier for physicians to manage the increasing demand and provide consistent diagnostic decisions more efficiently.

For instance, the new Cardio AI premium feature, Strain + AIPowered by 4D Flow provides cardiologists and radiologists with fast and reliable automated myocardial strain analysis. Another new feature allows cardiologists and radiologists to easily quantify volumes for both left and right atria in cardiac MRI images to aid in the diagnostic process. Arterys' Cardio AI clinical application has added another new feature that provides automatic wall thickness measurements to aid in the diagnosis process.

In addition to the Cardio AI enhancements, Arterys received its eighth FDA clearance. This additional FDA clearance makes Cardio AI's existing T1 + AI, and T2 quantification modules available for commercial use. These now-cleared modules offer a dedicated workflow for T1 and ECV, and T2 quantification, including multiple and global ROIs, and a graphical display of curves that provides users with intuitive, simple calculations for tissue characterization.

"Cardio AI is an integral part of our image interpretation and patient management," said Ali B Syed, M.D., at Stanford School of Medicine, Department of Radiology. "It significantly reduces the time necessary to generate useful information from our imaging. What used to take 30 minutes or more is now done, in many cases, before the patient is even off of the MRI table. It has also accelerated our adoption of techniques like T1 mapping and quantitative delayed enhancement because it dramatically reduces the effort to report these values."

"Cardio AI has been an invaluable tool in our practice to allow us faster processing of complex cardiac MR examinations with automated contouring not only for function but also tissue characterization saving us minutes of processing time on every single exam," said Melany B. Atkins, M.D., Division Chief, Body/Cardiovascular Imaging at Inova Fairfax Hospital. "Rapid processing of 4D Flow affords us the ability to evaluate complex congenital heart disease nearly real-time."

"With the addition of our new modules, we are able to accommodate a wide variety of users from community hospitals/physician centers to larger research centers and even pediatrics," said Michelle Buekes, Product Manager, Cardio AI at Arterys. "We are very excited to continue to work with our customers and partners to build upon and improve our product to meet the needs of an evolving and growing field."

Related Links:
Arterys