The University of Iowa
The University of Iowa News Services Home News Releases UI in the News Subscribe to UI News Contact Us

University of Iowa News Release

April 26, 2006

UI Research Team Receives $1 Million NIH Grant To Improve Medical Image Analysis

A team of engineering and medical researchers based at the University of Iowa has received a three-year, $1 million National Institutes of Health (NIH) grant to improve the analysis of multi-dimensional medical images of the human body.

Titled "Graph-Based Medical Image Segmentation in 3-D and 4-D," the project is in addition to a four-year, $1.3 million NIH heart-imaging grant that UI researchers received in March. Milan Sonka (left), professor of electrical and computer engineering in the UI College of Engineering and principal investigator on both projects, says that the new grant will lead to computer techniques general enough to be applied to a variety of multi-dimensional data sets, some including motion and multiple image sets acquired over time.

"A 4-D image is a 3-D image subjected to motion over time, such as the complex motion of a beating heart or moving joints," he says. "An example of a 5-D dataset could be a beating heart studied longitudinally at different points in time, such as before a patient receives his or her medication, post-medication, and, later still, post-surgery."

From a mathematical standpoint, the project involves trying to detect interacting surfaces within the human body in multiple dimensions and visualize them as geometric shapes, including cylinders, closed-surface shapes and shapes that change their topology, he says.

In addition to Sonka, the interdisciplinary engineering/medicine project includes co-principal investigator Xiaodong Wu, assistant professor of electrical and computer engineering and assistant professor of radiation oncology in the Roy J. and Lucille A. Carver College of Medicine; and Andreas Wahle, associate research engineer in electrical and computer engineering. Danny Chen, professor of computer science at the University of Notre Dame, is also collaborating on the project.

Sonka says that once developed, the new methods are expected to substantially improve the ability of researchers to perform automated and quantitative medical image analysis. He says, "The results of this research will likely be used in standard clinical care as a part of computer-aided medical diagnostic systems, as well as for medical imaging research, drug development and in epidemiologic and clinical trials."

STORY SOURCE: University of Iowa News Services, 300 Plaza Centre One, Suite 371, Iowa City, Iowa 52242-2500.

MEDIA CONTACT: Gary Galluzzo, 319-384-0009,