Artificial Intelligence | News | Insights | AiThority
[bsfp-cryptocurrency style=”widget-18″ align=”marquee” columns=”6″ coins=”selected” coins-count=”6″ coins-selected=”BTC,ETH,XRP,LTC,EOS,ADA,XLM,NEO,LTC,EOS,XEM,DASH,USDT,BNB,QTUM,XVG,ONT,ZEC,STEEM” currency=”USD” title=”Cryptocurrency Widget” show_title=”0″ icon=”” scheme=”light” bs-show-desktop=”1″ bs-show-tablet=”1″ bs-show-phone=”1″ custom-css-class=”” custom-id=”” css=”.vc_custom_1523079266073{margin-bottom: 0px !important;padding-top: 0px !important;padding-bottom: 0px !important;}”]

United Imaging’s Artificial Intelligence Subsidiary Wins in Facebook AI Research & NYU School of Medicine Global Competition

Breakthrough work in fast MR image reconstruction led by United Imaging’s Boston R&D office takes top prize in the first fastMRI Challenge

United Imaging, a global leader in advanced medical imaging and radiotherapy equipment, followed a strong appearance at the annual meeting of the Radiological Society of North America (RSNA) with a win in a competition jointly organized by Facebook AI Research and NYU Langone Health.

The company’s United Imaging Intelligence America subsidiary led out of Boston won top prize in the multi-coil 4x acceleration category, a clinically relevant challenge designed to accelerate MRI scans using artificial intelligence (AI). “Using AI to create highly accurate images from significantly smaller amounts of raw data could result in much faster scans,” commented Dr. Terrence Chen, CEO of United Imaging Intelligence America. “This could improve the patient experience and make scans more accessible.”

Read More: OptimalPlus Opens German Office and Partners with ZF

Fast and accurate MRI image reconstruction from under-sampled data is critically important in clinical practice. Compressed-sensing-based methods are widely used in image reconstruction, but the speed is slow. Deep-learning-based methods have shown promising advances in recent years, but recovering the fine details from highly under-sampled data is still challenging.

Related Posts
1 of 14,229

“Our AI scientists Dr. Shanhui Sun and Dr. Zhang Chen, and our intern Puyang Wang, developed a novel deep-learning-based method, Pyramid Convolutional Recurrent Neural Network (PC-RNN), to reconstruct the image from multiple scales. We can recover more of the finer details without creating false signals using this advanced technology,” explained Terrence Chen.

Read More: Worldwide Spending on AR/VR Expected to Reach $18.8 Billion in 2020, According to IDC

The company’s momentum continues to build globally as well as in the United States. During the recent annual RSNA meeting, United Imaging made three major announcements: the first digital mobile PET/CT (in a mobile operated by Shared Medical Services); a partnership with BAMF Health, an organization revolutionizing theranostics and precision medicine; and the uMR Omega,* the world’s first ultra-wide 75-cm MR system. United Imaging also announced the introduction of uAI technologies into key radiology systems with DELTA,* a deep learning enhancement to its uCT (Computed Tomography) 7 series; HYPER Deep Learning Reconstruction* in the routine PET/CT workflow of its uMI 550 system; and AI-Assisted Compressed Sensing (ACS)* full-coverage image acceleration for its uMR 780 system.

According to the fastMRI competition, a critical part of the evaluation of the winning teams was the judgment of radiologists. Competition representatives explained that it was important to hear from radiologists to ensure the technology will be adopted once it’s made broadly available.

Read More: Artificial Intelligence Will Facilitate Growth of Innovative Kinds of VR and AR Platforms

Leave A Reply

Your email address will not be published.