• AI
  • Molecular Imaging
  • CT
  • X-Ray
  • Ultrasound
  • MRI
  • Facility Management
  • Mammography

Grid computing assists MR brain analysis

Article

A group of researchers in the U.K. has developed a system that uses the principles of grid computing to develop custom reference images for MR brain interpretations. An infoRAD exhibit at the 2003 RSNA meeting explains how age- and gender-specific

A group of researchers in the U.K. has developed a system that uses the principles of grid computing to develop custom reference images for MR brain interpretations.

An infoRAD exhibit at the 2003 RSNA meeting explains how age- and gender-specific images can be drawn from a brain reference atlas to permit automated comparisons that can be used to develop a more accurate diagnosis.

Grid computing links computers in networks to achieve tasks that are processor intensive and otherwise possible only on supercomputers. Although becoming more common in the IT world, it is just beginning to appear in medical applications.

The system developed by the British research team links reference images from 200 brains and allows searches that can be customized. Reference images are averaged and the result used for comparisons that can be tailored to an individual.

In one example, images from a 67-year-old woman with early signs of Alzheimer's disease are compared with data from demographically similar images drawn from the system's brain atlas. The comparison shows that the woman's ventricles are at the 95th percentile in size, an indication that she is edging toward Alzheimer's disease.

The value of grid computing is that image registration can be a computer-intensive process, said research team member Dr. Rolf Heckemann, an informatics expert at the Hammersmith Hospital. Using the power of multiple computers makes possible a quick search for reference images and averaging of their data that can be used for comparisons with the subject's images in a region of interest.

Other registration tasks that might benefit from grid techniques include temporal matching of tissue changes and fusion matching of images. The goal is diagnostic decision support, Heckemann said. Eventually, the system could link distributed data repositories, as additional data help improve the confidence of the diagnosis.

Recent Videos
Employing AI in Detecting Subdural Hematomas on Head CTs: An Interview with Jeremy Heit, MD, PhD
Pertinent Insights into the Imaging of Patients with Marfan Syndrome
What New Brain MRI Research Reveals About Cannabis Use and Working Memory Tasks
Current and Emerging Legislative Priorities for Radiology in 2025
How Will the New FDA Guidance Affect AI Software in Radiology?: An Interview with Nina Kottler, MD, Part 2
A Closer Look at the New Appropriate Use Criteria for Brain PET: An Interview with Phillip Kuo, MD, Part 2
How Will the New FDA Guidance Affect AI Software in Radiology?: An Interview with Nina Kottler, MD, Part 1
A Closer Look at the New Appropriate Use Criteria for Brain PET: An Interview with Phillip Kuo, MD, Part 1
Teleradiology and Breast Imaging: Keys to Facilitating Personalized Service, Efficiency and Equity
Current and Emerging Insights on AI in Breast Imaging: An Interview with Mark Traill, MD, Part 3
Related Content
© 2025 MJH Life Sciences

All rights reserved.