SANTA CLARA, Calif., Sept. 14, 2018 — Intel and Philips have tested two healthcare use cases for deep learning inference models.
In these tests, Intel and Philips achieved a speed improvement of 188 × for a bone-age-prediction model, and a 38 × speed improvement for a lung-segmentation model over the baseline measurements using Intel Xeon Scalable processors and the OpenVINO toolkit.
“Intel Xeon Scalable processors appear to be the right solution for this type of artificial intelligence (AI) workload,” said Vijayananda J., chief architect and fellow of data science and AI at Philips HealthSuite Insights. “Our customers can use their existing hardware to its maximum potential, while still aiming to achieve quality output resolution at exceptional speeds.”
Central processing units (CPUs) such as Intel Xeon Scalable processors don’t have the same memory constraints as graphic processing units (GPUs) and can accelerate complex, hybrid workloads including larger, memory-intensive models typically found in medical imaging. For a large subset of AI workloads, Intel Xeon Scalable processors can better meet data scientists’ needs than GPU-based systems. As Philips found in the two recent tests, this enables the company to offer AI solutions at lower cost to its customers.
AI techniques such as object detection and segmentation can help radiologists identify issues faster and more accurately, which can translate to better prioritization of cases, better outcomes for more patients, and reduced costs for hospitals.