Medical errors are the third-greatest cause of death in the U.S.1 Among them, stroke patients are misdiagnosed 9 to 30 percent of the time in the ER.2 It is projected that there will be 3.4 million stroke victims by 2030, which will cause loss or extreme hardships for patients and their families while generating $240 billion in total direct and indirect costs.3

Artificial Intelligence (AI) technology is becoming increasingly critical for the fast detection of life-threatening intracranial hemorrhages (ICH) by reading image scans. AI solutions are well-suited to help ER physicians, who are under extreme pressure to make quick and accurate decisions, while treating a large number of patients. In emergency CT scanning, combining the skill of radiologists with AI-enabled capabilities can quickly, accurately, and automatically detect ICH in patients and may improve outcomes while containing costs for healthcare providers.

MaxQ AI Automates and Accelerates Suspected Intracranial Hemorrhage (ICH) Detection with AI-Driven Imaging Insight

Optimized for Intel® architecture, MaxQ AI uses Accipio lx technology to deliver 3.7X faster performance

Solution briefHealthcareMedical Diagnostics

Solution Brief | MaxQ AI Automates and Accelerates Suspected Intracranial Hemorrhage (ICH) Detection with AI-Driven Imaging Insight

MaxQ AI ICH Detection SoftwareMaxQ AI is committed to harnessing the power of AI to raise the level of acute care in hospitals. Expert results from innovative technologies can potentially save lives, improve quality, and lower healthcare costs. MaxQ AI is at the forefront of transforming healthcare by empowering physicians to provide smarter care through intelligent imaging with AI-driven actionable insights. The company is developing a suite of bedside, clinical, and diagnostic decision-making tools for treatment of head trauma and stroke, where every minute counts.

The ACCIPIO platform uses MaxQ AI’s lx technology to help clinicians quickly and accurately assess whether a patient has an ICH. Based on deep learning technologies, the acute imaging AI engine leverages deep vision and cognitive analytics to assess a wide range of features. Using these methods, the Accipio platform is capable of combining the full richness of medical imaging along with other relevant patient data.

Accipio lx and Accipio Ax are two products within this platform that are trained to automatically analyze CT images for ICH. Accipio Ix and Accipio Ax reduce the time needed to detect hemorrhages and may improve accuracy, enabling physicians to effectively prioritize patients when time is of the utmost importance.

Accipio Platform – AI With AnswersThe Accipio platform receives and processes non-contrast head CT images from any DICOM source in the hospital environment. The Accipio processing engine utilizes machine vision algorithms, Convolutional Neural Networks, and Deep Neural Networks of differing architectures. The processing engine is highly parallelized to maximize CPU utilization and reduce processing time. It is optimized for performance on Intel® processors.

High PrioritySuspected

StrokeSYSteM WitH

inteGrAteD ACCiPio Ax*

SuSPeCteD ACute iCH founD

PrioritiZe ACCelerAte AnnotAteWHo HAS A Subtle iCH?

?

??

??

??

?

2

Solution Brief | MaxQ AI Automates and Accelerates Suspected Intracranial Hemorrhage (ICH) Detection with AI-Driven Imaging Insight

Up to 3.7X Performance Increase on Intel® ArchitectureThe inference performance of Convolutional Neural Networks has been improved by using the Intel® Distribution of OpenVINO™ toolkit in the processing engine. These optimizations enabled the processing time to be improved by up to 3.7X on an Intel® Core™ i9 processor4 without impacting detection accuracy. The machine vision algorithms were also optimized for performance by using Intel® Threading Building Blocks (Intel® TBB) memory allocation methods to reduce context switching between threads. Further increase in performance was achieved by using OpenMP in place of boost thread pool.

ConclusionThe complete Accipio platform is designed to support the radiology, emergency room, and neuroradiology teams with a fully-automated solution. The Accipio platform uses MaxQ AI’s INSIGHT method, providing prioritization (Ix5) and annotation preview (Ax6) with further capabilities in development.

Running Accipio on Intel software and hardware platforms reduces processing time and contributes to a faster result for the medical team.

Learn MoreFor more information about the MaxQ AI’s Accipio platform, visit https://www.maxq.ai.

To learn more about the Intel® AI Builders program, visit https://builders.intel.com/ai.

Performance results are based on testing as of dates shown in configuration and may not reflect all publicly available security updates. No product or component can be absolutely secure. See configuration disclosure for details.

Optimization Notice: Intel’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 optimi-zations 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 microarchitec-ture 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. 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: http://www.intel.com/performance.

1 https://www.bmj.com/content/353/bmj.i2139 . 2 Neurology. 2017; 88(15):1468-77. doi: 10.1212/WNL.0000000000003814. 3 American Heart Association and American Stroke Association Policy Statement. “Forecasting the Future of Stroke in the United States.” Stroke. 2013; doi:10.1161/STR.0b013e31829734f2. 4 Baseline: Testing conducted JAN 2019, 1 socket Intel® Core™ i9-7960X, 16 cores per socket, OS Microsoft Windows Server* 2016 Standard, Kernel 10.0.14393 Build 14393, Total memory 64.0

GB, SMBIOS Version 3.0, Optimized: Testing conducted JAN 2019, 1 socket Intel® Core™ i9-7960X, 16 cores per socket, OS Microsoft Windows Server 2016 Standard, Kernel 10.0.14393 Build 14393, Total memory 64.0 GB, SMBIOS Version 3.0, Python 3.4, Caffe2 0.8.0 (stock), VTune 2019 Update1, OpenVINO SDK v3.34.

5 Accipio Ix: FDA Cleared, CE Approved, Commercially Available. 6 Accipio Ax: FDA Cleared, CE Approved, Commercially available. © Intel Corporation. Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as

the property of others. 1019/AU/HBD/PDF Please Recycle 341066-001US

MaxQ AI is a member of the Intel® AI Builders Program, an ecosystem of industry-leading independent software vendors (ISVs), system integrators (SIs), original equipment manufacturers (OEMs), and enterprise end users, which have a shared mission to accelerate the adoption of artificial intelligence across Intel® platforms.