Discipline:
Technology
Type of service:
Research Paper
Spacing:
Single spacing
Paper format:
APA
Number of pages:
1 page
Number of sources:
4 sources
Paper detalis:
What you have to
do is write a research project proposal You may write your project on
any topic that interests you or relate to your major. Please remember to
choose a “data rich” topic so that you can create the charts that are
required. If you are writing a paper for another course, you can “double
dip” because I’m just grading this based on your Word, Excel and
PowerPoint skills (see grading below).
down below is an example of how the research project proposal will look i also attached files
Medical Image Processing: Parallel Computing Algorithms
Wayne Cheng
CC, Dr. Lu
Definition and Goals
Research in high performance parallel computing algorithms is becoming
very important in medical image applications. My research goal is to
develop parallel computing algorithms to improve performance in
atlas-based segmentation framework, developed in Kent State University’s
Image Processing Lab.
Literature Review
Medical image analysis is shifting from the visual analysis of planar
images to the computerized quantitative analysis of volumetric images.
It is important to have high performance computing power to handle the
extra computation necessary for volumetric images [1]. The Atlas-based
segmentation framework procedure is composed of three stages:
• a rigid registration stage;
• non-rigid registration stage; and
• an atlas-based segmentation stage.
At each stage, the image processing tasks may not necessarily be
sequential; therefore, they can be divided into smaller tasks to be
carried out in parallel. Moreover, research groups in Europe are
working on medical image processing using grid computing [2]. Other
researchers have reported the use of parallel computing in their
research on medical image segmentation [3] and registration [4] for
improving image processing performance.
Research Plan
My research plan consists of the following sections:
1. Study and understand atlas-based segmentation framework in medical images processing.
2. Learn the ClearSpeed Application Programming Interface for parallel computing applications.
3. Divide and recognize tasks within each stage for suitable parallel computing sequences.
4. Design parallel computing algorithms for each stage.
5. Use designed parallel computing algorithms in ClearSpeed API to run experiments on each stage.
6. Validate the improvement on atlas-based segmentation framework performance base on previous work.
Developing parallel computing algorithms could improve atlas-based segmentation framework performance.
References
[1] S. Warfield, F. Jolesz, and R. Kikinis. A high performance
computing approach to the registration of medical imaging data.
Parallel Computing, 24(9-10):1345 – 1368, 1998.
[2] R. Stefanescu, X. Pennec, and N. Ayache. Grid powered nonlinear
image registration with locally adaptive reqularization. Medical Image
Analysis, 8(3):325 – 342, 2004
[3] Y. Fan, T. Jiang, and D. J. Evans. Volumetric segmentation of brain
images using parallel genetic algorithms. IEEE Trans. On Medical
Imaging, 21(8):904 – 909, Aug. 2002.
[4] T. Rohlfing and C. R. Maurer Jr. Nonrigid image registration in
shared-memory multiprocessor environments with application to brains,
breasts, and bees. IEEE Trans. Info. Tech. Bio., 7(1):16 – 25, 2003
0 comments