Logo of the CARDIA
Share |


Get the Flash Player to see this player.

Cardiovascular Informatics

The Need

Coronary heart disease (CHD) is still the major cause of death in most developed countries, including the United States. Every year, over 1.4 million Americans suffer a heart attack. About half of these heart attacks prove fatal, despite a host of new public health initiatives targeting heart disease and its aggravating factors such as obesity. Why? Because the majority of sudden cardiac deaths occur in individuals with no prior symptoms. That is, in many cases, the first symptom of CHD is death.

Developing the technologies necessary for successful screening of individuals at risk for heart disease is becoming progressively more critical as the number of fatal attacks increases. Those at risk for heart disease and its complications are referred to as "vulnerable patients." Cardiologists have agreed on a 3-tiered approach to assessment of patient vulnerability, characterized by

  • whole-body health (e.g., family history, blood tests, cholesterol count)
  • non-invasive imaging (CT and MR)
  • invasive imaging (intravascular ultrasound)
Progression up the "pyramid" leading to the need for more invasive tests can be avoided if suitable methods exist that detect CHD at an early stage (from non-invasive tests).

Our Goal

Our goal is to develop and validate a computational framework that will allow fusion and mining of a variety of imaging data to extract information that will allow the detection of vulnerable plaque, vulnerable myocardium, and vulnerable blood. This will in turn lead to the development of a quantitative method for cumulative risk assessment of vulnerable patients. Computer vision techniques developed by our group for this project so far include
  • Assessment of cardiac dynamics and function via 4-D left ventricle (LV) segmentation and 4-D coronary artery segmentation using MR and CT respectively.
  • Assessment of abdominal fat burden using CT.
  • Assessment of plaque inflammation using intravascular ultrasound-based vasa vasorum imaging.

Visitors are encouraged to browse the Gallery and other pages on this site. Please use the "Contact Us" link to reach the group if you have any questions related to our research.

Related links: