Intel, Philips tout speed gains in AI-powered healthcare algorithms

Intel (NSDQ:INTC) and Royal Philips (NYSE:PHG) said last week they are partnering to test Intel hardware’s ability to run deep learning artificial intelligence programs intended to improve the capabilities of Philips tech.

The two companies joined to test the abilities of hardware using Intel Xeon processors and the OpenVINO toolkit for two AI-powered programs: one for bone-age-prediction modeling based on X-rays and one examining computed tomography scans of lungs for segmentation.

Intel said that in the tests, the systems showed speed improvements of 188 times for the bone-age prediction model and 38 times for the lung-segmentation model over baseline measurements.

“The results for both use cases surpassed expectations. The bone-age-prediction model went from an initial baseline test result of 1.42 images per second to a final tested rate of 267.1 images per second after optimizations – an increase of 188 times. The lung-segmentation model far surpassed the target of 15 images per second by improving from a baseline of 1.9 images per second to 71.7 images per second after optimizations,” Intel wrote in a press release.

Intel said it is hopeful that their hardware systems will enable healthcare companies, like Philips, the ability to offer more fully functional AI algorithm-based solutions.

In June, Philips said that it inked an 11-year enterprise monitoring deal with Jackson Health System.

The post Intel, Philips tout speed gains in AI-powered healthcare algorithms appeared first on MassDevice.

from MassDevice https://ift.tt/2PsQ4xX