61. REAL-TIME HIGH CONTENT OPTICAL MAPPING SYSTEM

Department: Computer Science & Engineering
Faculty Advisor(s): Ryan Kastner
Award(s): Honorable Mention

Primary Student
Name: Pingfan Meng
Email: pmeng@ucsd.edu
Phone: 858-534-8908
Grad Year: 2015

Abstract
Hundreds of thousands of people die from heart attack in the U.S. every year. Cardiac dysrhythmia is known to be one of the most important reasons for heart attack. Optical mapping is a tool for researching cardiac dysrhythmia and preventing heart attack. However, the optical mapping algorithm is computationally intensive and consumes a considerable amount of time. For example, 12 seconds of data requires 5.5 hours of computation. Therefore, this article presents a GPU implementation of the optical mapping algorithm used in cardiac electrophysiology. We studied the efficiency of different input sizes and memory access methods. Our result shows that GPU implementation of the optical mapping algorithm has a 55X speedup over the equivalent CPU implementation.

« Back to Posters or Search Results