Siemens Healthineers and Intel Demonstrate the Potential of AI for Real-Time Cardiac MRI Diagnosis

What’s New : Intel and Siemens Healthineers are collaborating on a break-through artificial intelligence (AI)-based cardiac MRI segmentation and analysis model that has the potential to provide real-time cardiovascular disease diagnosis. Using 2nd-generation Intel Xeon Scalable processors for AI inference, Intel and Siemens Healthineers demonstrated the ability to deliver MRI inferencing results to technologists, cardiologists and radiologists in real time.

David Ryan, general manager, Health and Life Sciences Sector, Internet of Things Group, Intel said, “Siemens Healthineers and Intel have a shared goal to improve healthcare by applying AI where the data is generated — right at the edge using 2nd-generation Intel Xeon Scalable processors with Intel Deep Learning (DL) Boost and the Intel Distribution for OpenVINO. This enables real-time applications of cardiac MRI, making data interpretation available right after it’s collected.”

Why It’s Important : One-third of all deaths in the U.S. – 34 deaths a minute or 18 million deaths a year – are due to cardiovascular disease1. Cardiac MRI has established itself as a gold-standard for evaluating heart function, heart chamber volumes and myocardial tissue evaluation1. To extract quantitative measurements from the CMR images, the cardiologists typically use manual or semi-automatic tools, a time-consuming step that is error-prone and affected by the inter-user subjectivity in interpreting the images.

“We can now develop multiple real-time, often critical medical imaging use cases, such as cardiac MRI and others, using Intel Xeon Scalable processors, without the added cost or complexity of hardware accelerators,” said Dorin Comaniciu, senior vice president, Siemens Healthineers.

Utilizing an AI model of the heart potentially saves time for cardiologists because they do not have to manually segment different ventricles, myocardium, and blood pool cavities. AI-based segmentation happens as soon as the image slices are generated by the scanner – at the edge, where the computation system can keep pace with the data being generated. This provides low latency for AI inference and high throughput speed, enabling healthcare providers to safely increase the number of patients treated per day.

What Benefits It Offers : The health and life sciences industry is digitizing healthcare and utilizing AI to accelerate clinical workflows, improve accuracy and diagnosis, reduce hospital costs, and support medical research. AI can quickly provide visibility into anatomical systems and identify abnormalities, which helps clinicians focus patient care.

About the Technology : Most systems deployed by Siemens Healthineers are already powered by Intel CPUs, allowing Siemens Healthineers to leverage its existing CPU-based infrastructure to run AI inference workloads. Siemens Healthineers and Intel used the Intel Distribution of OpenVINO toolkit to optimize, quantify and execute the model. The resulting demonstration achieved a more than five times speed-up with almost no degradation in accuracy.

Intel DL Boost is a new set of embedded processor technologies designed to accelerate deep learning use cases. It extends Intel AVX-512 instructions with a new Vector Neural Network Instruction (VNNI), which is built into 2nd-generation Intel Xeon Scalable processors. Tasks such as convolutions, which typically required three instructions, can now be accomplished with just one instruction. Examples of these targeted workloads include image-recognition, image-segmentation, speech-recognition, language-translation, object-detection and more.

About Technology For You

Technology For You (TFY) is a Leading Technology & Career Magazine. In addition to the Print Edition, we have been bringing out Web Edition also with Daily News & Updates. This is one of the Largest Circulated magazine in South India, and also reaching across India.
View all posts by Technology For You →

Leave a Reply

Your email address will not be published. Required fields are marked *