Global Sources
EE Times-Asia
Stay in touch with EE Times Asia
EE Times-Asia > Optoelectronics/Displays

Image registration speeds up 3D medical images processing

Posted: 11 Apr 2007 ?? ?Print Version ?Bookmark and Share

Keywords:3D medical images? image registration? Cell Blade?

IBM Corp., along with U.S.-based medical center Mayo Clinic, has disclosed advancement in image registration, which utilized parallel computer architecture and memory bandwidth to speed up the processing of 3D medical images. Such progress helps in image registration, in which two computer-enhanced medical images are aligned at different dates or by using different imaging devices, in 3D space. With the images properly aligned over one another, a radiologist can detect structural changes such as the growth or shrinkage of tumors.

"This alignment of images improves both the accuracy of interpretation as well as radiologist efficiency, particularly for diseases like cancer," says Bradley Erickson, M.D., Ph.D., Mayo radiology researcher.

Through porting and optimization of Mayo Clinic's Image Registration Application on the IBM BladeCenter QS20 'Cell Blade,' the firms application produces image results almost 50 times faster than the application running on a traditional processor configuration.

One of the ways of improving medical images is by using visual images from more than one source such as MRI and CT scans. The generation of computer-enhanced images from multiple sources begins with accurate alignment of the visual data. The complexity of the task increases due to involvement of 3D and millions of pixels which lead to the need of higher processing speeds.

For the imaging project, Mayo Clinic and IBM used 98 sets of images and ran the optimized registration application on the IBM BladeCenter QS20. The team adapted a 'mutual-information-based' 3D linear registration algorithm application optimized for Cell/B.E. and completed the registration for all 98 sets of images in just 516sec, with none of the registrations taking more than 20sec.

The 3D linear algorithm finds the best spatial positioning to maximize the amount of information gathered from the two images, thus optimizing sampling quality while reducing sampling time. Greater efficiencies were achieved by caching data in cuboids or 'bricks', preventing loss of pixels during image sampling. In case of low sampling ratio, the sampled moving pixel images are packed in an 'image stripe' to retrieve speed when needed.

By running the application faster, a physician will be able to make quicker diagnosis and promptly begin appropriate treatments for patients.

"This is all about taking technology innovation, collaborating with our customers, and helping them directly benefit their patients," said Shahrokh Daijavad, next generation computing, systems & technology, IBM. "Besides allowing doctors and radiologists to achieve in seconds what used to take hours, the improvement in the application running on Cell also decreases the waiting time and anxiety of a patient."

Article Comments - Image registration speeds up 3D medi...
*? You can enter [0] more charecters.
*Verify code:


Visit Asia Webinars to learn about the latest in technology and get practical design tips.

Back to Top