Sudden heart attacks remain the leading cause of death in the US. Heart attacks are caused by complications of "vulnerable plaques." The discovery of vulnerable plaques has recently evolved into the definition of the "vulnerable patient" (VP). A VP is defined as a person with a high likelihood of developing a heart attack in the near future. Since the majority of sudden cardiac deaths occur in people with no prior symptoms, there is an urgent need for computational tools to assist in screening for the conditions that underlie sudden cardiac events.
This project is developing the theoretical framework and computational tools for the mining of information from CT and intravascular ultrasound (IVUS) imaging for the detection of VPs. The specific objectives are to: (1) develop new denoising algorithms; (2) develop a new medical image segmentation framework; (3) develop new enhancement quantification techniques; and (4) apply these techniques and evaluate their performance to the problems of CT and IVUS-based detection of VPs. The project's collaborating cardiovascular specialists at the Association for the Eradication of Heart Attack believe that such methods hold the potential to contribute to the development of a quantitative method for early detection and intervention to improve outcomes and increase survival.
A new course on Cardiovascular Informatics offered at the undergraduate and graduate levels will allow the integration of this research into education. Outreach materials will be created in collaboration with the Pearland (TX) Independent School District, the Houston Area Technology Advancement Center, and the Houston Museum of Natural Science.
