Propagating interactive segmentation of a single 3D example to similar images: An evaluation study using MR images of the prostate

Emmanouil Moschidis; Jim Graham

doi:10.1109/ISBI.2011.5872678

Propagating interactive segmentation of a single 3D example to similar images: An evaluation study using MR images of the prostate

Emmanouil Moschidis, Jim Graham

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper we address the problem of segmentation propagation from one example onto similar images in an on-line and real-time fashion. As suggested in [1], we consider segmentation as a process consisting of two stages: the localization of the anatomy of interest and its boundary delineation. For each stage we identify and evaluate different potential candidate methods. All methods are applied on a dataset of 22 three dimensional (3-D) Magnetic Resonance (MR) images of the prostate. The high variation of appearance of the prostate across individuals is a challenging feature, which affects the repeatability of frameworks that leverage prior knowledge from one image example. Our observation is that the repeatability of the framework is improved, when a two stage processing strategy is realized, based on the deformable registration of [6,7], followed by Graph-Cuts [11,12] based segmentation. © 2011 IEEE.

Original language	English
Title of host publication	Proceedings - International Symposium on Biomedical Imaging\|IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn.
Publisher	IEEE
Pages	1472-1475
Number of pages	3
ISBN (Print)	9781424441280
DOIs	https://doi.org/10.1109/ISBI.2011.5872678
Publication status	Published - 2011
Event	2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 - Chicago, IL Duration: 1 Jul 2011 → …

Conference

Conference	2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11
City	Chicago, IL
Period	1/07/11 → …

Keywords

3-D Medical Images
Graph-Cuts
Image Registration
Image Segmentation
Performance Evaluation
Prostate Segmentation

Access to Document

10.1109/ISBI.2011.5872678

Cite this

@inproceedings{48b3f6d407e84005b36cf1e3bc24b797,

title = "Propagating interactive segmentation of a single 3D example to similar images: An evaluation study using MR images of the prostate",

abstract = "In this paper we address the problem of segmentation propagation from one example onto similar images in an on-line and real-time fashion. As suggested in [1], we consider segmentation as a process consisting of two stages: the localization of the anatomy of interest and its boundary delineation. For each stage we identify and evaluate different potential candidate methods. All methods are applied on a dataset of 22 three dimensional (3-D) Magnetic Resonance (MR) images of the prostate. The high variation of appearance of the prostate across individuals is a challenging feature, which affects the repeatability of frameworks that leverage prior knowledge from one image example. Our observation is that the repeatability of the framework is improved, when a two stage processing strategy is realized, based on the deformable registration of [6,7], followed by Graph-Cuts [11,12] based segmentation. {\textcopyright} 2011 IEEE.",

keywords = "3-D Medical Images, Graph-Cuts, Image Registration, Image Segmentation, Performance Evaluation, Prostate Segmentation",

author = "Emmanouil Moschidis and Jim Graham",

year = "2011",

doi = "10.1109/ISBI.2011.5872678",

language = "English",

isbn = "9781424441280",

pages = "1472--1475",

booktitle = "Proceedings - International Symposium on Biomedical Imaging|IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn.",

publisher = "IEEE",

address = "United States",

note = "2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 ; Conference date: 01-07-2011",

}

Moschidis, E & Graham, J 2011, Propagating interactive segmentation of a single 3D example to similar images: An evaluation study using MR images of the prostate. in Proceedings - International Symposium on Biomedical Imaging|IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn.. IEEE, pp. 1472-1475, 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11, Chicago, IL, 1/07/11. https://doi.org/10.1109/ISBI.2011.5872678

Propagating interactive segmentation of a single 3D example to similar images: An evaluation study using MR images of the prostate. / Moschidis, Emmanouil; Graham, Jim.

Proceedings - International Symposium on Biomedical Imaging|IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn.. IEEE, 2011. p. 1472-1475.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Propagating interactive segmentation of a single 3D example to similar images: An evaluation study using MR images of the prostate

AU - Moschidis, Emmanouil

AU - Graham, Jim

PY - 2011

Y1 - 2011

N2 - In this paper we address the problem of segmentation propagation from one example onto similar images in an on-line and real-time fashion. As suggested in [1], we consider segmentation as a process consisting of two stages: the localization of the anatomy of interest and its boundary delineation. For each stage we identify and evaluate different potential candidate methods. All methods are applied on a dataset of 22 three dimensional (3-D) Magnetic Resonance (MR) images of the prostate. The high variation of appearance of the prostate across individuals is a challenging feature, which affects the repeatability of frameworks that leverage prior knowledge from one image example. Our observation is that the repeatability of the framework is improved, when a two stage processing strategy is realized, based on the deformable registration of [6,7], followed by Graph-Cuts [11,12] based segmentation. © 2011 IEEE.

AB - In this paper we address the problem of segmentation propagation from one example onto similar images in an on-line and real-time fashion. As suggested in [1], we consider segmentation as a process consisting of two stages: the localization of the anatomy of interest and its boundary delineation. For each stage we identify and evaluate different potential candidate methods. All methods are applied on a dataset of 22 three dimensional (3-D) Magnetic Resonance (MR) images of the prostate. The high variation of appearance of the prostate across individuals is a challenging feature, which affects the repeatability of frameworks that leverage prior knowledge from one image example. Our observation is that the repeatability of the framework is improved, when a two stage processing strategy is realized, based on the deformable registration of [6,7], followed by Graph-Cuts [11,12] based segmentation. © 2011 IEEE.

KW - 3-D Medical Images

KW - Graph-Cuts

KW - Image Registration

KW - Image Segmentation

KW - Performance Evaluation

KW - Prostate Segmentation

U2 - 10.1109/ISBI.2011.5872678

DO - 10.1109/ISBI.2011.5872678

M3 - Conference contribution

SN - 9781424441280

SP - 1472

EP - 1475

BT - Proceedings - International Symposium on Biomedical Imaging|IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn.

PB - IEEE

T2 - 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11

Y2 - 1 July 2011

ER -

Propagating interactive segmentation of a single 3D example to similar images: An evaluation study using MR images of the prostate

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this