Make Breakthroughs in Medical Imaging Technology

X-rays, magnetic resonance imaging (MRI), computed tomography (CT) imaging, and ultrasounds generate about 600 million scans a year—and that number is growing.1 With a trusted history of providing advanced technologies for medical imaging systems, Intel is addressing several challenges in the market:

  • Compute options. OEMs and ODMs are designing solutions across a diverse range of form factors, from mobile ultrasound to nuclear medicine. Each form factor has its own unique compute requirements. Intel offers a range of CPUs that meet the needs of any imaging modality.
  • Scalable platforms. The medical imaging industry is moving toward more standardized computing platforms that can be shared across modalities to lower costs and accelerate innovation. Intel supports scalability with an unmatched product portfolio that includes compute, storage, memory, and networking, backed by extensive software resources. We can help with resources for full-stack platforms that support today’s most challenging workloads and tomorrow’s designs.
  • Edge-to-cloud deployment. The ability to flexibly deploy workloads at the edge and in the cloud is quickly becoming the status quo. Edge computing in particular allows providers to analyze images and make decisions at the point of care. This near-real-time medical image analysis can enable faster decisions that help save lives. With our broad range of solutions and deep partner ecosystem, Intel enables a modern edge-to-cloud architecture.
  • Artificial intelligence. AI is revealing new ways to streamline workflows and is becoming a de facto capability in imaging systems. For example, deep learning in medical imaging can help prioritize images for a patient with a potentially fatal brain bleed over others in the queue. In other cases, AI can help evaluate images quickly and accurately while removing variances. AI can even help with patient positioning, which can mean the difference between a useful image and the inconvenience of a retake. Intel offers hardware with built-in AI acceleration, plus optimized software. Our demonstrated success in AI ranges from helping deploy deep learning models on in-market modalities to designing mobile systems that can run AI without connectivity.
  • Developer enablement. To gain traction in the medical imaging marketplace, software developers building AI-enabled applications need to provide complete solutions and differentiated capabilities. Applications must meet an extensive range of accuracy, cost, customer deployment, and scalability requirements. Intel offers a broad array of tools and programs designed to help software developers successfully develop, launch, and scale new medical imaging AI applications that meet the needs of the healthcare market.

At Intel, our work is informed by strong partnerships within the healthcare ecosystem, from major healthcare systems to developers and software vendors. Together, we’re harnessing AI, edge computing, and other advanced technologies to power digital transformation in medical imaging technology.

Advancing Medical Imaging With Intel® Solutions

Intel® Vision Product Portfolio

Intel® software streamlines the development of AI-based medical imaging solutions across a range of hardware—CPUs, VPUs, GPUs, and FPGAs. This portfolio of hardware and software enables the healthcare industry to make the most of medical imaging data and provide better patient experiences.

See Intel® Vision Products ›

Carestream Delivers Medical Images from the Cloud

To work efficiently, clinicians must be able to quickly call up MRIs, CT scans, and other images from any device they’re using. Backed by Intel® Xeon® Scalable processors and Intel® Optane™ technology, Carestream provides a solution that makes medical records affordable and readily accessible to users.

Learn more ›

See More Customer Stories


Artificial Intelligence in Medical Imaging Technology

Intel is at the forefront of advancing technologies that enable the medical imaging market to adopt AI. Intel hardware is already used in many areas of medical imaging technology, so running AI models on the same architecture is a natural progression. We offer hardware, software, and expertise to address a wide range of needs, including:

  • Retrofitting in-market systems with the ability to run AI models
  • Deploying AI seamlessly across edge environments and the cloud
  • Developing scalable AI platforms to run today’s most challenging algorithms with a foundation for tomorrow's future innovations

Explore AI ›

Explore Advanced Medical Imaging Technology at the Intel® Solutions Marketplace


Notices and Disclaimers

Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors.

Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems, components, software, operations, and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products. For more complete information visit intel.com/benchmarks.

Intel does not control or audit third-party data. You should consult other sources to evaluate accuracy.

Intel® technologies may require enabled hardware, software, or service activation.

No product or component can be absolutely secure.

Your costs and results may vary.

Product and Performance Information

1“Medical Imaging Market Analysis, Size, Trends,” MedSuite, 2016, https://idataresearch.com/product/medical-imaging-market-united-states/.
2

Lung Nodule Detection from CT Scan Using Intel® Processors, QuEST Global white paper, builders.intel.com/docs/aibuilders/lung-nodule-detection-from-ct-scan-using-intel-processors.pdf.

3

GE Healthcare’s AIRx™ Tool Accelerates Magnetic Resonance Imaging using Intel® AI Technologies, Intel white paper, intel.com/content/www/us/en/artificial-intelligence/solutions/gehc-airx.html.

4

Intel and GE Healthcare Partner to Advance AI in Medical Imaging,” Intel Customer Spotlight, intel.co.uk/content/www/uk/en/customer-spotlight/stories/ge-healthcare-medical-imaging.html.

5Intel’s compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel® microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel® microprocessors. Certain optimizations not specific to Intel® microarchitecture are reserved for Intel® microprocessors. Please refer to the applicable product user and reference guides for more information regarding the specific instruction sets covered by this notice.
6Intel’s compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product user and reference guides for more information regarding the specific instruction sets covered by this notice.
7System test configuration disclosure: Intel® Core™ i5-4590S CPU @ 3.00 GHz, x86_64, VT-x enabled, 16 GB memory, OS: Linux magic x86_64 GNU/Linux, Ubuntu 16.04 inferencing service docker container. Testing done by GE Healthcare, September 2018. Test compares TensorFlow model total inferencing time of 3.092 seconds to the same model optimized by the Intel® Distribution of OpenVINO™ toolkit optimized TF model resulting in a total inferencing time of 0.913 seconds.