Incorporating user input in template-based segmentation

Camille Vidal, Dale Beggs, Laurent Younes, Sanjay Jain, Bruno Jedynak

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

Abstract

We present a simple and elegant method to incorporate user input in a template-based segmentation method for diseased organs. The user provides a partial segmentation of the organ of interest, which is used to guide the template towards its target. The user also highlights some elements of the background that should be excluded from the final segmentation. We derive by likelihood maximization a registration algorithm from a simple statistical image model in which the user labels are modeled as Bernoulli random variables. The resulting registration algorithm minimizes the sum of square differences between the binary template and the user labels, while preventing the template from shrinking, and penalizing for the inclusion of background elements into the final segmentation. We assess the performance of the proposed algorithm on synthetic images in which the amount of user annotation is controlled. We demonstrate our algorithm on the segmentation of the lungs of Mycobacterium tuberculosis infected mice from μCT images.

Original languageEnglish (US)
Title of host publicationProceedings - International Symposium on Biomedical Imaging
Pages1434-1437
Number of pages4
DOIs
StatePublished - 2011
Event2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 - Chicago, IL, United States
Duration: Mar 30 2011Apr 2 2011

Other

Other2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11
CountryUnited States
CityChicago, IL
Period3/30/114/2/11

Fingerprint

Labels
Statistical Models
Mycobacterium tuberculosis
Random variables
Lung

Keywords

  • Diseased Organs
  • Registration
  • Template-based Segmentation
  • User Input

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Vidal, C., Beggs, D., Younes, L., Jain, S., & Jedynak, B. (2011). Incorporating user input in template-based segmentation. In Proceedings - International Symposium on Biomedical Imaging (pp. 1434-1437). [5872669] https://doi.org/10.1109/ISBI.2011.5872669

Incorporating user input in template-based segmentation. / Vidal, Camille; Beggs, Dale; Younes, Laurent; Jain, Sanjay; Jedynak, Bruno.

Proceedings - International Symposium on Biomedical Imaging. 2011. p. 1434-1437 5872669.

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

Vidal, C, Beggs, D, Younes, L, Jain, S & Jedynak, B 2011, Incorporating user input in template-based segmentation. in Proceedings - International Symposium on Biomedical Imaging., 5872669, pp. 1434-1437, 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11, Chicago, IL, United States, 3/30/11. https://doi.org/10.1109/ISBI.2011.5872669
Vidal C, Beggs D, Younes L, Jain S, Jedynak B. Incorporating user input in template-based segmentation. In Proceedings - International Symposium on Biomedical Imaging. 2011. p. 1434-1437. 5872669 https://doi.org/10.1109/ISBI.2011.5872669
Vidal, Camille ; Beggs, Dale ; Younes, Laurent ; Jain, Sanjay ; Jedynak, Bruno. / Incorporating user input in template-based segmentation. Proceedings - International Symposium on Biomedical Imaging. 2011. pp. 1434-1437
@inproceedings{f5f8fd492f8143b0bce841cc43326012,
title = "Incorporating user input in template-based segmentation",
abstract = "We present a simple and elegant method to incorporate user input in a template-based segmentation method for diseased organs. The user provides a partial segmentation of the organ of interest, which is used to guide the template towards its target. The user also highlights some elements of the background that should be excluded from the final segmentation. We derive by likelihood maximization a registration algorithm from a simple statistical image model in which the user labels are modeled as Bernoulli random variables. The resulting registration algorithm minimizes the sum of square differences between the binary template and the user labels, while preventing the template from shrinking, and penalizing for the inclusion of background elements into the final segmentation. We assess the performance of the proposed algorithm on synthetic images in which the amount of user annotation is controlled. We demonstrate our algorithm on the segmentation of the lungs of Mycobacterium tuberculosis infected mice from μCT images.",
keywords = "Diseased Organs, Registration, Template-based Segmentation, User Input",
author = "Camille Vidal and Dale Beggs and Laurent Younes and Sanjay Jain and Bruno Jedynak",
year = "2011",
doi = "10.1109/ISBI.2011.5872669",
language = "English (US)",
isbn = "9781424441280",
pages = "1434--1437",
booktitle = "Proceedings - International Symposium on Biomedical Imaging",

}

TY - GEN

T1 - Incorporating user input in template-based segmentation

AU - Vidal, Camille

AU - Beggs, Dale

AU - Younes, Laurent

AU - Jain, Sanjay

AU - Jedynak, Bruno

PY - 2011

Y1 - 2011

N2 - We present a simple and elegant method to incorporate user input in a template-based segmentation method for diseased organs. The user provides a partial segmentation of the organ of interest, which is used to guide the template towards its target. The user also highlights some elements of the background that should be excluded from the final segmentation. We derive by likelihood maximization a registration algorithm from a simple statistical image model in which the user labels are modeled as Bernoulli random variables. The resulting registration algorithm minimizes the sum of square differences between the binary template and the user labels, while preventing the template from shrinking, and penalizing for the inclusion of background elements into the final segmentation. We assess the performance of the proposed algorithm on synthetic images in which the amount of user annotation is controlled. We demonstrate our algorithm on the segmentation of the lungs of Mycobacterium tuberculosis infected mice from μCT images.

AB - We present a simple and elegant method to incorporate user input in a template-based segmentation method for diseased organs. The user provides a partial segmentation of the organ of interest, which is used to guide the template towards its target. The user also highlights some elements of the background that should be excluded from the final segmentation. We derive by likelihood maximization a registration algorithm from a simple statistical image model in which the user labels are modeled as Bernoulli random variables. The resulting registration algorithm minimizes the sum of square differences between the binary template and the user labels, while preventing the template from shrinking, and penalizing for the inclusion of background elements into the final segmentation. We assess the performance of the proposed algorithm on synthetic images in which the amount of user annotation is controlled. We demonstrate our algorithm on the segmentation of the lungs of Mycobacterium tuberculosis infected mice from μCT images.

KW - Diseased Organs

KW - Registration

KW - Template-based Segmentation

KW - User Input

UR - http://www.scopus.com/inward/record.url?scp=80055030438&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80055030438&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2011.5872669

DO - 10.1109/ISBI.2011.5872669

M3 - Conference contribution

C2 - 26146532

AN - SCOPUS:80055030438

SN - 9781424441280

SP - 1434

EP - 1437

BT - Proceedings - International Symposium on Biomedical Imaging

ER -