Imaging equipment manufacturers are getting their first taste of an advanced processor that could boost the speed of image reconstruction by several orders of magnitude while delivering better image quality.
Imaging equipment manufacturers are getting their first taste of an advanced processor that could boost the speed of image reconstruction by several orders of magnitude while delivering better image quality.
Mercury Computer began shipping its Cell Technology Evaluation System (CTES) in mid-January. CTES is based on the Dual Cell-Based Blade shown at the RSNA 2005 meeting. The turnkey system features the IBM Cell Broadband Engine (BE) processor and an Intel architecture development/simulation environment. It comes equipped with Mercury, IBM, and open-source Cell Technology software.
The evaluation units are being distributed to OEMs in the medical imaging industry as well as companies in other markets, including defense and industrial inspection. They will enable Mercury customers to evaluate Cell BE processor-based computing solutions and begin prototyping advanced applications.
Cell is a relative newcomer, having been introduced only last summer. It combines eight synergistic computing elements and a controller into a single 64-bit central processing unit, all sharing the same memory and delivering a peak performance of more than 200 billion operations per second. Blade BE integrates two Cell processors and a memory chip on a single computer board.
At the RSNA meeting, Mercury branded its role in the industry with the slogan "3D to the core." The slogan represents a corporate strategy to provide OEMs with the computing horsepower to easily integrate 3D visualization into their equipment. This strategy embraces Cell technology while transcending it to encompass Mercury's Visage software. This software is designed to accelerate image reconstruction. Speeds of 40 to 60 times current capabilities are possible using this software, providing advanced 3D imaging for such modalities as CT, MR, ultrasound, digital x-ray, molecular imaging, and breast tomosynthesis.
Mercury's software-based Visage CS (client/server) empowers PCs with 3D capabilities otherwise found on stand-alone workstations, according to the company. Commands issued on a PC are executed so rapidly by Visage CS that reconstructions appear as though they were done live onboard the PC. Visage CS could be plugged into legacy hospital IT systems, eliminating a hospital's reliance on a few expensive 3D workstations.
The technology is being tested now at major institutions, including the Baltimore VA Medical Center, which is affiliated with the University of Maryland, where luminaries are examining the clinical impact of integrating 3D into PACS.
CTES represents a hardware-oriented approach, although the technology depends heavily on Mercury programming. CTES is integrated with Mercury's MultiCore Framework software to optimize the transfer of data among Cell BE processors. This framework is part of the Mercury MultiCore Plus Advantage, which employs sophisticated middleware that abstracts hardware capabilities and manages the distribution of data across multiple computing elements working together. It includes patented cooling technologies, lightweight system-on-chip management software, multicore implementations of key algorithms, visualization tools designed for clusters, algorithm tuning, and more.
Thousands of currently installed CTs, MRs, and PACS use Mercury-built computer boards that rapidly process the signals acquired during scans or the data needed for volumetric reconstructions. This new breed of Mercury components, built around the company's Dual Cell-Based Blade BE, could substantially boost processing power.
Blade BE, the first product of this technology, is scheduled to begin production at the end of this year in response to orders expected from companies now evaluating the technology.
The second module of this new breed could be packed with as many as four processors. The Turismo is composed of several boards and, therefore, requires more space, about as much as a PC tower. It is scheduled to begin shipping to OEMs for evaluation in late summer. Production of this component is planned for early 2007.
Faster data handling is leveraged to run complex data filters that improve image quality. These filters are particularly important to getting the best quality images when doing dynamic or iterative reconstructions, according to Marcelo G. Lima, Mercury's vice president of life sciences and of commercial imaging and visualization solutions.
"You can go for brute force speed, or you can go for image-quality improvements," he said. "Either way, Cell technology will change how we do things."
Cell was developed as part of a joint venture by IBM, Toshiba, and Sony Group to handle the kind of rapid image rendering demanded by high-performance video games. Cell will appear later this year in Sony's PlayStation 3 and in a line of that company's high-definition television systems.
IBM approached Mercury in early 2005 with the idea of developing this technology for applications outside consumer electronics. Mercury has since incorporated Cell into defense, life sciences, seismic, and industrial applications.
Other companies can license the Cell technology from IBM, Lima said, but Mercury has a unique advantage in leveraging Cell given its decades-long experience in developing computing components for the imaging industry. Because Mercury sells its components to any and all vendors, rather than entering into exclusive supplier agreements, the benefits will be felt throughout the imaging community.
The Reading Room: Racial and Ethnic Minorities, Cancer Screenings, and COVID-19
November 3rd 2020In this podcast episode, Dr. Shalom Kalnicki, from Montefiore and Albert Einstein College of Medicine, discusses the disparities minority patients face with cancer screenings and what can be done to increase access during the pandemic.
Study: AI Model Significantly Enhances CTA Workflow Efficiency and Detection for Cerebral Aneurysm
October 18th 2024Adjunctive use of deep learning reportedly led to a 37 percent reduction of interpretation time for cerebral aneurysm assessment on computed tomography angiography (CTA) and greater than a 90 percent reduction in post-processing time.