Fast and Robust Multi-Modal Image Registration for 3D Knee Kinematics

Shabnam Saadat, Mark R. Pickering, Diana Perriman, Jennie M. Scarvell, Paul N. Smith

Research output: A Conference proceeding or a Chapter in BookConference contribution

3 Citations (Scopus)

Abstract

The process of spatially aligning two or more images acquired from different devices or imaging protocols is known as multi-modal image registration. As the similarity measure used is one of the most significant aspects of this process, certain measures have been proposed to enhance multi-modal image registration. However, the currently available measures are either not sufficiently accurate or are very computationally expensive. In this paper, a new hybrid multimodal registration approach is proposed. The new approach combines a fast measure, based on matching image edges, with a robust, but slow measure, which uses the joint probability distribution of the two images to be registered. Our experimental results reveal that using this hybrid approach provides a performance equivalent to the previously best measures but with a significantly reduced computational time.

Original languageEnglish
Title of host publicationDICTA 2017 - 2017 International Conference on Digital Image Computing
Subtitle of host publicationTechniques and Applications
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1-5
Number of pages5
Volume2017-December
ISBN (Electronic)9781538628393
DOIs
Publication statusPublished - 19 Dec 2017
Event2017 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2017 - Sydney, Australia
Duration: 29 Nov 20171 Dec 2017

Conference

Conference2017 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2017
CountryAustralia
CitySydney
Period29/11/171/12/17

Fingerprint

Image registration
Kinematics
Image matching
Probability distributions
Imaging techniques

Cite this

Saadat, S., Pickering, M. R., Perriman, D., Scarvell, J. M., & Smith, P. N. (2017). Fast and Robust Multi-Modal Image Registration for 3D Knee Kinematics. In DICTA 2017 - 2017 International Conference on Digital Image Computing: Techniques and Applications (Vol. 2017-December, pp. 1-5). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/DICTA.2017.8227434
Saadat, Shabnam ; Pickering, Mark R. ; Perriman, Diana ; Scarvell, Jennie M. ; Smith, Paul N. / Fast and Robust Multi-Modal Image Registration for 3D Knee Kinematics. DICTA 2017 - 2017 International Conference on Digital Image Computing: Techniques and Applications. Vol. 2017-December IEEE, Institute of Electrical and Electronics Engineers, 2017. pp. 1-5
@inproceedings{427bef138ac641f9af3254dd7539e0fb,
title = "Fast and Robust Multi-Modal Image Registration for 3D Knee Kinematics",
abstract = "The process of spatially aligning two or more images acquired from different devices or imaging protocols is known as multi-modal image registration. As the similarity measure used is one of the most significant aspects of this process, certain measures have been proposed to enhance multi-modal image registration. However, the currently available measures are either not sufficiently accurate or are very computationally expensive. In this paper, a new hybrid multimodal registration approach is proposed. The new approach combines a fast measure, based on matching image edges, with a robust, but slow measure, which uses the joint probability distribution of the two images to be registered. Our experimental results reveal that using this hybrid approach provides a performance equivalent to the previously best measures but with a significantly reduced computational time.",
keywords = "edge detection, image registration, medical images, similarity measure, sum-of-conditional variance",
author = "Shabnam Saadat and Pickering, {Mark R.} and Diana Perriman and Scarvell, {Jennie M.} and Smith, {Paul N.}",
year = "2017",
month = "12",
day = "19",
doi = "10.1109/DICTA.2017.8227434",
language = "English",
volume = "2017-December",
pages = "1--5",
booktitle = "DICTA 2017 - 2017 International Conference on Digital Image Computing",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Saadat, S, Pickering, MR, Perriman, D, Scarvell, JM & Smith, PN 2017, Fast and Robust Multi-Modal Image Registration for 3D Knee Kinematics. in DICTA 2017 - 2017 International Conference on Digital Image Computing: Techniques and Applications. vol. 2017-December, IEEE, Institute of Electrical and Electronics Engineers, pp. 1-5, 2017 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2017, Sydney, Australia, 29/11/17. https://doi.org/10.1109/DICTA.2017.8227434

Fast and Robust Multi-Modal Image Registration for 3D Knee Kinematics. / Saadat, Shabnam; Pickering, Mark R.; Perriman, Diana; Scarvell, Jennie M.; Smith, Paul N.

DICTA 2017 - 2017 International Conference on Digital Image Computing: Techniques and Applications. Vol. 2017-December IEEE, Institute of Electrical and Electronics Engineers, 2017. p. 1-5.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Fast and Robust Multi-Modal Image Registration for 3D Knee Kinematics

AU - Saadat, Shabnam

AU - Pickering, Mark R.

AU - Perriman, Diana

AU - Scarvell, Jennie M.

AU - Smith, Paul N.

PY - 2017/12/19

Y1 - 2017/12/19

N2 - The process of spatially aligning two or more images acquired from different devices or imaging protocols is known as multi-modal image registration. As the similarity measure used is one of the most significant aspects of this process, certain measures have been proposed to enhance multi-modal image registration. However, the currently available measures are either not sufficiently accurate or are very computationally expensive. In this paper, a new hybrid multimodal registration approach is proposed. The new approach combines a fast measure, based on matching image edges, with a robust, but slow measure, which uses the joint probability distribution of the two images to be registered. Our experimental results reveal that using this hybrid approach provides a performance equivalent to the previously best measures but with a significantly reduced computational time.

AB - The process of spatially aligning two or more images acquired from different devices or imaging protocols is known as multi-modal image registration. As the similarity measure used is one of the most significant aspects of this process, certain measures have been proposed to enhance multi-modal image registration. However, the currently available measures are either not sufficiently accurate or are very computationally expensive. In this paper, a new hybrid multimodal registration approach is proposed. The new approach combines a fast measure, based on matching image edges, with a robust, but slow measure, which uses the joint probability distribution of the two images to be registered. Our experimental results reveal that using this hybrid approach provides a performance equivalent to the previously best measures but with a significantly reduced computational time.

KW - edge detection

KW - image registration

KW - medical images

KW - similarity measure

KW - sum-of-conditional variance

UR - http://www.scopus.com/inward/record.url?scp=85048252875&partnerID=8YFLogxK

U2 - 10.1109/DICTA.2017.8227434

DO - 10.1109/DICTA.2017.8227434

M3 - Conference contribution

VL - 2017-December

SP - 1

EP - 5

BT - DICTA 2017 - 2017 International Conference on Digital Image Computing

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

Saadat S, Pickering MR, Perriman D, Scarvell JM, Smith PN. Fast and Robust Multi-Modal Image Registration for 3D Knee Kinematics. In DICTA 2017 - 2017 International Conference on Digital Image Computing: Techniques and Applications. Vol. 2017-December. IEEE, Institute of Electrical and Electronics Engineers. 2017. p. 1-5 https://doi.org/10.1109/DICTA.2017.8227434