Improved Elastic Medical Image Registration Using Mutual Information

Konstantin Ens; Hanno Schumacher; Astrid Franz; Bernd Fischer; J.P.W. Pluim; J.M. Reinhardt

doi:10.1117/12.707632

Improved Elastic Medical Image Registration Using Mutual Information

Konstantin Ens, Hanno Schumacher, Astrid Franz, Bernd Fischer, J.P.W. Pluim, J.M. Reinhardt

Institute of Mathematics

Abstract

One of the future-oriented areas of medical image processing is to develop fast and exact algorithms for image registration. By joining multi-modal images we are able to compensate the disadvantages of one imaging modality with the advantages of another modality. For instance, a Computed Tomography (CT) image containing the anatomy can be combined with metabolic information of a Positron Emission Tomography (PET) image. It is quite conceivable that a patient will not have the same position in both imaging systems. Furthermore some regions for instance in the abdomen can vary in shape and position due to different filling of the rectum. So a multi-modal image registration is needed to calculate a deformation field for one image in order to maximize the similarity between the two images, described by a so-called distance measure. In this work, we present a method to adapt a multi-modal distance measure, here mutual information (MI), with weighting masks. These masks are used to enhance relevant image structures and suppress image regions which otherwise would disturb the registration process. The performance of our method is tested on phantom data and real medical images.

Original language	English
Title of host publication	Medical Imaging 2007: Image Processing
Editors	Joseph M. Reinhardt, Josien P. W. Pluim
Number of pages	8
Place of Publication	San Diego, CA, United States
Publisher	SPIE
Publication date	08.03.2007
Pages	6512 - 6512 - 8
Article number	65122C
ISBN (Print)	978-081946630-3
DOIs	https://doi.org/10.1117/12.707632
Publication status	Published - 08.03.2007
Event	Medical Imaging 2007: Image Processing - San Diego, United States Duration: 17.02.2007 → 22.02.2007 Conference number: 70570

Access to Document

10.1117/12.707632

Cite this

Ens, K., Schumacher, H., Franz, A., Fischer, B., Pluim, J. P. W., & Reinhardt, J. M. (2007). Improved Elastic Medical Image Registration Using Mutual Information. In J. M. Reinhardt, & J. P. W. Pluim (Eds.), Medical Imaging 2007: Image Processing (pp. 6512 - 6512 - 8). Article 65122C (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 6512). SPIE. https://doi.org/10.1117/12.707632

@inproceedings{2105aff18bf8473694f6270e0ca180e8,

title = "Improved Elastic Medical Image Registration Using Mutual Information",

abstract = "One of the future-oriented areas of medical image processing is to develop fast and exact algorithms for image registration. By joining multi-modal images we are able to compensate the disadvantages of one imaging modality with the advantages of another modality. For instance, a Computed Tomography (CT) image containing the anatomy can be combined with metabolic information of a Positron Emission Tomography (PET) image. It is quite conceivable that a patient will not have the same position in both imaging systems. Furthermore some regions for instance in the abdomen can vary in shape and position due to different filling of the rectum. So a multi-modal image registration is needed to calculate a deformation field for one image in order to maximize the similarity between the two images, described by a so-called distance measure. In this work, we present a method to adapt a multi-modal distance measure, here mutual information (MI), with weighting masks. These masks are used to enhance relevant image structures and suppress image regions which otherwise would disturb the registration process. The performance of our method is tested on phantom data and real medical images.",

author = "Konstantin Ens and Hanno Schumacher and Astrid Franz and Bernd Fischer and J.P.W. Pluim and J.M. Reinhardt",

year = "2007",

month = mar,

day = "8",

doi = "10.1117/12.707632",

language = "English",

isbn = "978-081946630-3",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

pages = "6512 -- 6512 -- 8",

editor = "Reinhardt, {Joseph M. } and Pluim, {Josien P. W. }",

booktitle = "Medical Imaging 2007: Image Processing",

note = "Medical Imaging 2007: Image Processing ; Conference date: 17-02-2007 Through 22-02-2007",

}

Ens, K, Schumacher, H, Franz, A, Fischer, B, Pluim, JPW & Reinhardt, JM 2007, Improved Elastic Medical Image Registration Using Mutual Information. in JM Reinhardt & JPW Pluim (eds), Medical Imaging 2007: Image Processing ., 65122C, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 6512, SPIE, San Diego, CA, United States, pp. 6512 - 6512 - 8, Medical Imaging 2007: Image Processing, San Diego, California, United States, 17.02.07. https://doi.org/10.1117/12.707632

Improved Elastic Medical Image Registration Using Mutual Information. / Ens, Konstantin; Schumacher, Hanno; Franz, Astrid et al.
Medical Imaging 2007: Image Processing . ed. / Joseph M. Reinhardt; Josien P. W. Pluim. San Diego, CA, United States: SPIE, 2007. p. 6512 - 6512 - 8 65122C (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 6512).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Improved Elastic Medical Image Registration Using Mutual Information

AU - Ens, Konstantin

AU - Schumacher, Hanno

AU - Franz, Astrid

AU - Fischer, Bernd

AU - Pluim, J.P.W.

AU - Reinhardt, J.M.

N1 - Conference code: 70570

PY - 2007/3/8

Y1 - 2007/3/8

N2 - One of the future-oriented areas of medical image processing is to develop fast and exact algorithms for image registration. By joining multi-modal images we are able to compensate the disadvantages of one imaging modality with the advantages of another modality. For instance, a Computed Tomography (CT) image containing the anatomy can be combined with metabolic information of a Positron Emission Tomography (PET) image. It is quite conceivable that a patient will not have the same position in both imaging systems. Furthermore some regions for instance in the abdomen can vary in shape and position due to different filling of the rectum. So a multi-modal image registration is needed to calculate a deformation field for one image in order to maximize the similarity between the two images, described by a so-called distance measure. In this work, we present a method to adapt a multi-modal distance measure, here mutual information (MI), with weighting masks. These masks are used to enhance relevant image structures and suppress image regions which otherwise would disturb the registration process. The performance of our method is tested on phantom data and real medical images.

AB - One of the future-oriented areas of medical image processing is to develop fast and exact algorithms for image registration. By joining multi-modal images we are able to compensate the disadvantages of one imaging modality with the advantages of another modality. For instance, a Computed Tomography (CT) image containing the anatomy can be combined with metabolic information of a Positron Emission Tomography (PET) image. It is quite conceivable that a patient will not have the same position in both imaging systems. Furthermore some regions for instance in the abdomen can vary in shape and position due to different filling of the rectum. So a multi-modal image registration is needed to calculate a deformation field for one image in order to maximize the similarity between the two images, described by a so-called distance measure. In this work, we present a method to adapt a multi-modal distance measure, here mutual information (MI), with weighting masks. These masks are used to enhance relevant image structures and suppress image regions which otherwise would disturb the registration process. The performance of our method is tested on phantom data and real medical images.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-36248954475&origin=inward&txGid=8ea305e614ce15ffe2bd8ffb9ef08f05

U2 - 10.1117/12.707632

DO - 10.1117/12.707632

M3 - Conference contribution

SN - 978-081946630-3

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

SP - 6512 - 6512 - 8

BT - Medical Imaging 2007: Image Processing

A2 - Reinhardt, Joseph M.

A2 - Pluim, Josien P. W.

PB - SPIE

CY - San Diego, CA, United States

T2 - Medical Imaging 2007: Image Processing

Y2 - 17 February 2007 through 22 February 2007

ER -

Ens K, Schumacher H, Franz A, Fischer B, Pluim JPW, Reinhardt JM. Improved Elastic Medical Image Registration Using Mutual Information. In Reinhardt JM, Pluim JPW, editors, Medical Imaging 2007: Image Processing . San Diego, CA, United States: SPIE. 2007. p. 6512 - 6512 - 8. 65122C. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). doi: 10.1117/12.707632

Improved Elastic Medical Image Registration Using Mutual Information

Abstract

Access to Document

Other files and links

Fingerprint

Cite this