To have a better experience, please upgrade your IE browser.upgrade
If you need help, please click here:
Healthcare has once again fallen under the spotlight, given the current global situation. Medical science has undoubtedly improved rapidly, extending life expectancy across the globe. But as people live longer, medical systems are witnessing vast growth in demand for services, which jacks up the cost and pushes the healthcare workforce to deliver top-notch services to the patients.
Automation is among the most crucial tech breakthroughs in the sector, and Artificial Intelligence (AI) is a powerful tool to let to success. But when it comes to healthcare, there is a common myth: With AI, we are expecting robots to take over doctors and nurses, rendering people obsolete. Patients may entrust to machines – rather than doctors – to make difficult decisions.
However, AI is not replacing doctors. Instead, it is helping them improve diagnostic accuracy and efficiency. Artificial Intelligence does its work in accessing substantial data sets of potentially life-saving information, such as treatment methods and their outcomes, and other data like survival rates, etc.
Therefore, incorporating AI into clinical workflow helps streamlining medical procedures for doctors. The ultimate goal is to work with doctors and medical professional to improve healthcare services via the fair use of AI. On this front, three significant developments are expected.
The first one is medical imagery analysis, which is one key area that requires an upgrade with the support of AI. Primary medical imaging represents a tremendous potential for growth due to its increasing demand. With the help of AI, such imaging service gets a significant boost in resolving the mismatch of demand and supply among the current medical services.
In some countries, there are as many as two-thirds of primary hospitals serving merely 20% of patients requiring diagnosis and treatment. There could be some 10% of the medical institutions classified as tertiary, where more than a third of patients are seeking service there.
The resource mismatch represents another trend – AI empowers the primary medical service, further alleviating the imbalance between supply and demand of existing medical services. And the shortage of radiologists in primary medical institutions is getting more alarming than ever.
Further observed in the area of medical imagery is the combination of hardware and software. The integration of AI algorithm and hardware is imperative, breaking through the physical limitations of hardware and improving the intelligent density, measured by computing power per unit area.
Simply put, the AI algorithm works with hardware to boost intelligence density and lower the cost of building up the system. The demand for computing, meanwhile, will keep going up to meet the AI requirements for various scenarios in the new digital era. For AI to work effectively, it takes both software and hardware together – neither one could handle alone.
So with the power of AI, the application of imagery is brought to another level, where radiologists have more significant roles in the clinical decision-making process. Intelligence diagnosis systems are now used in chest examination, and for child’s growth and development, so that radiologists can have more participation in giving advises upon the results.
YITU Healthcare is a leading firm in the imagery sector, which integrates cutting-edge AI technologies with different applications to provide precise analysis for timely diagnosis. In response to the ongoing COVID-19 pandemic, YITU Healthcare provides the Automatic Evaluation System of chest CT for COVID-19.
The system can automatically analyze and classify pneumonia severity within just three seconds, compared to the traditional manual evaluation process that usually takes two to three hours.
The automatic system also runs a dynamic 4D comparison of whole lung lesions with multiple CT examinations for more treatment evaluations. It can automatically compare a patient’s historical and current records, which is highly consistent with doctors’ diagnosis.
A similar system – one that supports multiple standards – is applied for evaluation of children’s bone age, where a diagnosis can be made within just seconds. Like in other systems, it gives consistent evaluation results with doctors, while delivering comprehensive and customized growth and development reports.
It is now commonly used for children’s bone age assessment within a condensed timeframe: less than five minutes for X-ray, evaluation and reporting.
All these solutions require tremendous computing power to provide accurate and timely analysis. And it is made possible by Huawei’s Atlas series, which supports a wide range of medical scenarios – they usually demand huge computing power for the best results.
The Atlas series covers device, edge, to cloud computing settings, with the core at Atlas 300I inference card and Atlas 800 inference server to provide the power image and video analysis, shortening CT scan analysis to just two minutes, with an accuracy of over 98%.
The Atlas 300I card boasts around 33% more computing power with doubling the number of full-HD video channels than some available products in the market.
Meanwhile, the Atlas 800 server comes with two Kunpeng 920 processors, 32 DD4 DIMM slots supporting up to 2,933 MT/s plus as many as eight Atlas 300I cards leading to a maximum of 640 channels for intelligent video analytics.
It is a powerful server setting that works best for real-time inference and training that demands high efficiency at low power consumption. Pairing up with the Atlas 300 dedicated decoding engine, the Atlas 800 server performs remarkably for real-time transcoding and inference of up to 512 video streams.
The innovative use of resources – computing power up to 512 TOPS at INT8 – allows not just much faster diagnosis but also a vast boost in accuracy thanks to the improved the recognition precision.
With an open setting, the server supports cloud-edge collaboration and provides various software development kits. It is highly flexible, working perfectly well with FlexIO cards and standard iNICs with storage of enormous capacity, making the system reliable and secure.
For more information, please visit here.