Table of Contents Author Guidelines Submit a Manuscript
International Journal of Reconfigurable Computing
Volume 2008, Article ID 738174, 17 pages
Research Article

Multiobjective Optimization for Reconfigurable Implementation of Medical Image Registration

1Department of Electrical and Computer Engineering, University of Maryland, College Park, MD 20742, USA
2Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD 21201, USA

Received 6 March 2008; Revised 11 September 2008; Accepted 27 November 2008

Academic Editor: Juergen Becker

Copyright © 2008 Omkar Dandekar et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


In real-time signal processing, a single application often has multiple computationally intensive kernels that can benefit from acceleration using custom or reconfigurable hardware platforms, such as field-programmable gate arrays (FPGAs). For adaptive utilization of resources at run time, FPGAs with capabilities for dynamic reconfiguration are emerging. In this context, it is useful for designers to derive sets of efficient configurations that trade off application performance with fabric resources. Such sets can be maintained at run time so that the best available design tradeoff is used. Finding a single, optimized configuration is difficult, and generating a family of optimized configurations suitable for different run-time scenarios is even more challenging. We present a novel multiobjective wordlength optimization strategy developed through FPGA-based implementation of a representative computationally intensive image processing application: medical image registration. Tradeoffs between FPGA resources and implementation accuracy are explored, and Pareto-optimized wordlength configurations are systematically identified. We also compare search methods for finding Pareto-optimized design configurations and demonstrate the applicability of search based on evolutionary techniques for identifying superior multiobjective tradeoff curves. We demonstrate feasibility of this approach in the context of FPGA-based medical image registration; however, it may be adapted to a wide range of signal processing applications.