Simultaneous registration, segmentation and modelling of structure in groups of medical images

V. Petrović; T. Cootes; C. Twining; C. Taylor; Vladimir Petrovic

doi:10.1109/ISBI.2007.356773

Simultaneous registration, segmentation and modelling of structure in groups of medical images

V. Petrović, T. Cootes, C. Twining, C. Taylor, Vladimir Petrovic

Research output: Chapter in Book/Conference proceeding › Conference contribution

Abstract

We address the problem of extracting information from groups of medical images of the same anatomy. We describe an algorithm which simultaneously segments and registers a set of such images, incrementally constructing a model of their structure and the correspondences across the set. The framework explicitly models the fraction of each tissue type, rather than the expected intensity in each voxel, to decouple the model from details of the imaging sequence and modality. When estimating the optimal deformation field, the current image is compared to a reconstructed image, generated from the model tissue fractions and the current estimate of intensity distributions for each tissue type in the current image (i.e. an estimate of how the model would appear given the imaging conditions for that image). We describe the algorithm in detail and present results of applying it to a set of MR images of the brain. © 2007 IEEE.

Original language	English
Title of host publication	2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings\|IEEE Int. Symp. Biomed. Imag. Nano Macro Proc.
Publisher	IEEE
Pages	1-4
Number of pages	3
ISBN (Print)	1424406722, 9781424406722
DOIs	https://doi.org/10.1109/ISBI.2007.356773
Publication status	Published - 2007
Event	2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro; ISBI'07 - Arlington, VA Duration: 1 Jul 2007 → …

Conference

Conference	2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro; ISBI'07
City	Arlington, VA
Period	1/07/07 → …

Keywords

Image registration
Segmentation
Structure modelling of medical images

Access to Document

10.1109/ISBI.2007.356773

Cite this

Petrović, V., Cootes, T., Twining, C., Taylor, C., & Petrovic, V. (2007). Simultaneous registration, segmentation and modelling of structure in groups of medical images. In 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings|IEEE Int. Symp. Biomed. Imag. Nano Macro Proc. (pp. 1-4). IEEE. https://doi.org/10.1109/ISBI.2007.356773

@inproceedings{b982c3a3748f4545a341314e305476ab,

title = "Simultaneous registration, segmentation and modelling of structure in groups of medical images",

abstract = "We address the problem of extracting information from groups of medical images of the same anatomy. We describe an algorithm which simultaneously segments and registers a set of such images, incrementally constructing a model of their structure and the correspondences across the set. The framework explicitly models the fraction of each tissue type, rather than the expected intensity in each voxel, to decouple the model from details of the imaging sequence and modality. When estimating the optimal deformation field, the current image is compared to a reconstructed image, generated from the model tissue fractions and the current estimate of intensity distributions for each tissue type in the current image (i.e. an estimate of how the model would appear given the imaging conditions for that image). We describe the algorithm in detail and present results of applying it to a set of MR images of the brain. {\textcopyright} 2007 IEEE.",

keywords = "Image registration, Segmentation, Structure modelling of medical images",

author = "V. Petrovi{\'c} and T. Cootes and C. Twining and C. Taylor and Vladimir Petrovic",

year = "2007",

doi = "10.1109/ISBI.2007.356773",

language = "English",

isbn = "1424406722",

pages = "1--4",

booktitle = "2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings|IEEE Int. Symp. Biomed. Imag. Nano Macro Proc.",

publisher = "IEEE",

address = "United States",

note = "2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro; ISBI'07 ; Conference date: 01-07-2007",

}

Petrović, V, Cootes, T, Twining, C, Taylor, C & Petrovic, V 2007, Simultaneous registration, segmentation and modelling of structure in groups of medical images. in 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings|IEEE Int. Symp. Biomed. Imag. Nano Macro Proc.. IEEE, pp. 1-4, 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro; ISBI'07, Arlington, VA, 1/07/07. https://doi.org/10.1109/ISBI.2007.356773

Simultaneous registration, segmentation and modelling of structure in groups of medical images. / Petrović, V.; Cootes, T.; Twining, C. et al.
2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings|IEEE Int. Symp. Biomed. Imag. Nano Macro Proc.. IEEE, 2007. p. 1-4.

Research output: Chapter in Book/Conference proceeding › Conference contribution

TY - GEN

T1 - Simultaneous registration, segmentation and modelling of structure in groups of medical images

AU - Petrović, V.

AU - Cootes, T.

AU - Twining, C.

AU - Taylor, C.

AU - Petrovic, Vladimir

PY - 2007

Y1 - 2007

N2 - We address the problem of extracting information from groups of medical images of the same anatomy. We describe an algorithm which simultaneously segments and registers a set of such images, incrementally constructing a model of their structure and the correspondences across the set. The framework explicitly models the fraction of each tissue type, rather than the expected intensity in each voxel, to decouple the model from details of the imaging sequence and modality. When estimating the optimal deformation field, the current image is compared to a reconstructed image, generated from the model tissue fractions and the current estimate of intensity distributions for each tissue type in the current image (i.e. an estimate of how the model would appear given the imaging conditions for that image). We describe the algorithm in detail and present results of applying it to a set of MR images of the brain. © 2007 IEEE.

AB - We address the problem of extracting information from groups of medical images of the same anatomy. We describe an algorithm which simultaneously segments and registers a set of such images, incrementally constructing a model of their structure and the correspondences across the set. The framework explicitly models the fraction of each tissue type, rather than the expected intensity in each voxel, to decouple the model from details of the imaging sequence and modality. When estimating the optimal deformation field, the current image is compared to a reconstructed image, generated from the model tissue fractions and the current estimate of intensity distributions for each tissue type in the current image (i.e. an estimate of how the model would appear given the imaging conditions for that image). We describe the algorithm in detail and present results of applying it to a set of MR images of the brain. © 2007 IEEE.

KW - Image registration

KW - Segmentation

KW - Structure modelling of medical images

U2 - 10.1109/ISBI.2007.356773

DO - 10.1109/ISBI.2007.356773

M3 - Conference contribution

SN - 1424406722

SN - 9781424406722

SP - 1

EP - 4

BT - 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings|IEEE Int. Symp. Biomed. Imag. Nano Macro Proc.

PB - IEEE

T2 - 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro; ISBI'07

Y2 - 1 July 2007

ER -

Simultaneous registration, segmentation and modelling of structure in groups of medical images

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this