High performance medical image registration using a distributed blackboard architecture

Roger J. Tait*, Gerald Schaefer, Adrian A. Hopgood, Tomoharu Nakashima

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A major drawback of medical image registration techniques is the performance bottleneck associated with similarity computation. Such bottlenecks limit registration applications in situations where fast execution times are required. In this paper a novel framework for high performance intensity-based medical image registration is presented. Geometric alignment of both reference and sensed images is achieved through a combination of scaling, translation, and rotation. Crucially, similarity computation is performed intelligently by knowledge sources (KSs) organised in a worker/manager model. The KSs work in parallel and communicate with each other by means of a distributed blackboard architecture. Partitioning of the blackboard is used to balance communication and processing workloads. The registration framework presented demonstrates the flexibility of the coarse-grained parallelism employed and shows how high performance medical image registration can be achieved with non-specialised architectures. Experimental results obtained during testing show that substantial speedups can be achieved.

Original languageEnglish
Title of host publicationProceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007
PublisherIEEE
Pages252-257
Number of pages6
ISBN (Print)1424407079, 9781424407071
DOIs
Publication statusPublished - 25 Sep 2007
Event2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007 - Honolulu, HI, United Kingdom
Duration: 1 Apr 20075 Apr 2007

Conference

Conference2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007
CountryUnited Kingdom
CityHonolulu, HI
Period1/04/075/04/07

Fingerprint

Image registration
Managers
Communication
Testing
Processing

Cite this

Tait, R. J., Schaefer, G., Hopgood, A. A., & Nakashima, T. (2007). High performance medical image registration using a distributed blackboard architecture. In Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007 (pp. 252-257). [4221427] IEEE. https://doi.org/10.1109/CIISP.2007.369177
Tait, Roger J. ; Schaefer, Gerald ; Hopgood, Adrian A. ; Nakashima, Tomoharu. / High performance medical image registration using a distributed blackboard architecture. Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007. IEEE, 2007. pp. 252-257
@inproceedings{454902461cbf4691a866b5da647df8c0,
title = "High performance medical image registration using a distributed blackboard architecture",
abstract = "A major drawback of medical image registration techniques is the performance bottleneck associated with similarity computation. Such bottlenecks limit registration applications in situations where fast execution times are required. In this paper a novel framework for high performance intensity-based medical image registration is presented. Geometric alignment of both reference and sensed images is achieved through a combination of scaling, translation, and rotation. Crucially, similarity computation is performed intelligently by knowledge sources (KSs) organised in a worker/manager model. The KSs work in parallel and communicate with each other by means of a distributed blackboard architecture. Partitioning of the blackboard is used to balance communication and processing workloads. The registration framework presented demonstrates the flexibility of the coarse-grained parallelism employed and shows how high performance medical image registration can be achieved with non-specialised architectures. Experimental results obtained during testing show that substantial speedups can be achieved.",
author = "Tait, {Roger J.} and Gerald Schaefer and Hopgood, {Adrian A.} and Tomoharu Nakashima",
year = "2007",
month = "9",
day = "25",
doi = "10.1109/CIISP.2007.369177",
language = "English",
isbn = "1424407079",
pages = "252--257",
booktitle = "Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007",
publisher = "IEEE",
address = "United States",

}

Tait, RJ, Schaefer, G, Hopgood, AA & Nakashima, T 2007, High performance medical image registration using a distributed blackboard architecture. in Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007., 4221427, IEEE, pp. 252-257, 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007, Honolulu, HI, United Kingdom, 1/04/07. https://doi.org/10.1109/CIISP.2007.369177

High performance medical image registration using a distributed blackboard architecture. / Tait, Roger J.; Schaefer, Gerald; Hopgood, Adrian A.; Nakashima, Tomoharu.

Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007. IEEE, 2007. p. 252-257 4221427.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - High performance medical image registration using a distributed blackboard architecture

AU - Tait, Roger J.

AU - Schaefer, Gerald

AU - Hopgood, Adrian A.

AU - Nakashima, Tomoharu

PY - 2007/9/25

Y1 - 2007/9/25

N2 - A major drawback of medical image registration techniques is the performance bottleneck associated with similarity computation. Such bottlenecks limit registration applications in situations where fast execution times are required. In this paper a novel framework for high performance intensity-based medical image registration is presented. Geometric alignment of both reference and sensed images is achieved through a combination of scaling, translation, and rotation. Crucially, similarity computation is performed intelligently by knowledge sources (KSs) organised in a worker/manager model. The KSs work in parallel and communicate with each other by means of a distributed blackboard architecture. Partitioning of the blackboard is used to balance communication and processing workloads. The registration framework presented demonstrates the flexibility of the coarse-grained parallelism employed and shows how high performance medical image registration can be achieved with non-specialised architectures. Experimental results obtained during testing show that substantial speedups can be achieved.

AB - A major drawback of medical image registration techniques is the performance bottleneck associated with similarity computation. Such bottlenecks limit registration applications in situations where fast execution times are required. In this paper a novel framework for high performance intensity-based medical image registration is presented. Geometric alignment of both reference and sensed images is achieved through a combination of scaling, translation, and rotation. Crucially, similarity computation is performed intelligently by knowledge sources (KSs) organised in a worker/manager model. The KSs work in parallel and communicate with each other by means of a distributed blackboard architecture. Partitioning of the blackboard is used to balance communication and processing workloads. The registration framework presented demonstrates the flexibility of the coarse-grained parallelism employed and shows how high performance medical image registration can be achieved with non-specialised architectures. Experimental results obtained during testing show that substantial speedups can be achieved.

UR - http://www.scopus.com/inward/record.url?scp=34548707225&partnerID=8YFLogxK

U2 - 10.1109/CIISP.2007.369177

DO - 10.1109/CIISP.2007.369177

M3 - Conference contribution

AN - SCOPUS:34548707225

SN - 1424407079

SN - 9781424407071

SP - 252

EP - 257

BT - Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007

PB - IEEE

ER -

Tait RJ, Schaefer G, Hopgood AA, Nakashima T. High performance medical image registration using a distributed blackboard architecture. In Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007. IEEE. 2007. p. 252-257. 4221427 https://doi.org/10.1109/CIISP.2007.369177