OEMs harness video game technologies for use in advanced visualization

Article

The video game industry is changing radiology. Video graphics cards have become so powerful and inexpensive that the makers of imaging equipment are using them to enhance 2D and 3D rendering.

The video game industry is changing radiology. Video graphics cards have become so powerful and inexpensive that the makers of imaging equipment are using them to enhance 2D and 3D rendering.

The change is the result largely of the video game industry's adoption of OpenGL as a standard for graphics cards. This move has significantly cut the cost of manufacturing the cards, allowing the industry to focus on increasing their power.

Most monitor vendors now support OpenGL, which allows advanced visualization companies to focus on creating integrated, user-friendly solutions for the clinical analysis of digital medical images.

"For high-resolution monitors, we used to have to develop software for a proprietary library that supported that monitor to get good performance," said Mark Gehring, chief technical officer of Emageon in Birmingham, AL. "Now that vendors support OpenGL, we can use standard graphics cards. But, more important, we have one standard way of doing things."

PACS developer Emageon is one of the first imaging companies to take advantage of OpenGL. It has already released a software package using OpenGL for 2D imaging and plans to release OpenGL for 3D navigation in the fourth quarter of 2005.

Speed has been the key to this future. The scroll speed on high-resolution monitors has always been challenging, Gehring said. In the worst-case scenario, scroll speed might be five to 10 frames per second on a full screen. With the new high-performance graphics cards, the rate increases to 30 to 100 frames per second, depending on the monitor and card.

"Thirty frames per second on a full screen on a 3- or 5-megapixel monitor is not possible on most systems today. We are able to do that with OpenGL," Gehring said.

To achieve a fast scroll ratet for 2D imaging, vendors resorted in the pas to tricks such as a technique called "nearest neighbor interpolation." Results can look grainy. The smoother alternative, linear interpolation, is a computationally intensive algorithm that cannot be done on a full screen with most systems.

Because OpenGL's computing is all done on the hardware - the graphics card - it allows a company like Emageon to offer linear interpolation in its most basic package.

The same is true with 3D volume rendering. Most vendors use shortcut methods to rotate 3D images and present the final image. These images are still high quality, but the most accurate way to produce a 3D image from CT or MR data is using a ray tracing technique, Gehring said. Like linear interpolation, ray tracing is computationally intensive, but the new graphics cards can handle it with ease.

Emageon is leveraging OpenGL to boost the postprocessing performance of its PACS. With this, radiologists can have a hanging protocol that might include a 3D volume-rendered image in one view port, a multiplanar reconstruction in a second, and other protocols in a third.

"It's all part of the workflow and the user interface is consistent," Gehring said. "Radiologists do not have to learn a different set of tools to use the 3D imaging."

Typically, radiologists using a PACS go to a different workstation to manipulate 3D images, or they might have better integration that allows them to launch another application on the same workstation. Because that is a different application, they can't allow them to build it into a hanging protocol, he said.

"With ours, you use one system, and 3D is in that system," he said.

The entire application is Web-enabled. Radiologists can log on remotely and take advantage of the same 3D tools - not a Web version of that viewer, but the same viewer.

Because these and future advances are possible thanks to OpenGL, the imaging community can expect to see more such advances from other vendors. As these cards continue to drop in price and increase in power, OEMs will create more powerful and cost-effective equipment.

Recent Videos
SNMMI: Emerging PET Insights on Neuroinflammation with Progressive Apraxia of Speech (PAOS) and Parkinson-Plus Syndrome
Improving Access to Nuclear Imaging: An Interview with SNMMI President Jean-Luc C. Urbain, MD, PhD
SNMMI: 18F-Piflufolastat PSMA PET/CT Offers High PPV for Local PCa Recurrence Regardless of PSA Level
SNMMI: NIH Researcher Discusses Potential of 18F-Fluciclovine for Multiple Myeloma Detection
SNMMI: What Tau PET Findings May Reveal About Modifiable Factors for Alzheimer’s Disease
Emerging Insights on the Use of FES PET for Women with Lobular Breast Cancer
Can Generative AI Reinvent Radiology Reporting?: An Interview with Samir Abboud, MD
Mammography Study Reveals Over Sixfold Higher Risk of Advanced Cancer Presentation with Symptom-Detected Cancers
Combining Advances in Computed Tomography Angiography with AI to Enhance Preventive Care
Study: MRI-Based AI Enhances Detection of Seminal Vesicle Invasion in Prostate Cancer
Related Content
© 2025 MJH Life Sciences

All rights reserved.