Intel and Philips announced that they have joined forces to work on artificial intelligence (AI) by using Intel’s Xeon Scalable processors and OpenVINO toolkit to test two use cases for deep learning inference models. One case focused on using x-rays for bone-age-prediction modeling, and the other was CT scans of lungs for lung segmentation.
Overall, the companies reported that their technology made their bone-age-prediction model 188 times faster than normal and lung segmentation 38 times faster.
While the bone-age-prediction model jumped from a baseline of 1.42 images per second to 267.1 images per second, the lung-segmentation model increased from 1.9 images per second to 71.7 images per second.
“Intel Xeon Scalable processors appear to be the right solution for this type of AI workload,” Vijayananda J., chief architect and fellow of data science and AI at Philips HealthSuite Insights, said in a prepared statement. “Our customers can use their existing hardware to its maximum potential, while still aiming to achieve quality output resolution at exceptional speeds.”
Graphics processing units are typically used to accelerate deep learning, but Intel says central processing units such as the Xeon Scalable processors “can better meet data scientists’ needs.”
The full case studies are available on Intel’s website.