Sign In

Communications of the ACM

ACM TechNews

To Diagnose Heart Disease, Visualization Experts Recommend a Simpler Approach


Hanspeter Pfister and Michelle Borkin

Professor Hanspeter Pfister and Michelle Borkin study computer visualization tools at Harvard SEAS.

Credit: Courtesy of Harvard

Harvard University researchers have developed HemoVis, a method for visualizing human arteries that, in clinical testing, increased diagnostic accuracy from 39 percent to 91 percent.

HemoVis creates a two-dimensional (2D) diagram that is more effective than the traditional three-dimensional, rainbow-colored model. The researchers say their visualization method offers insight to clinicians, imaging specialists, engineers, and others in a wide range of fields who need to explore and evaluate complex, branching structures. "Our goal was to design a visual representation of the data that was as accurate and efficient for patient diagnosis as possible," says Harvard researcher Michelle Borkin.

HemoVis utilizes 2D, circumference-adjusted cylindrical cross sections arranged in tree diagrams, leading to consistently fast, accurate results. The system uses a graded single-color scheme that can represent placement along a continuum, fading from red to black.

"This approach to visualization design and validation is broadly applicable in medicine, engineering, and science," says Harvard professor Hanspeter Pfister.

From Harvard University
View Full Article

Abstracts Copyright © 2011 Information Inc. External Link, Bethesda, Maryland, USA 

 


 

No entries found