Robust segmentation using non-parametric snakes with multiple cues for applications in radiation oncology

Jayashree Kalpathy-Cramer, Umut Ozertem, William (Bill) Hersh, Martin Fuss, Deniz Erdogmus

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

2 Citations (Scopus)

Abstract

Radiation therapy is one of the most effective treatments used in the treatment of about half of all people with cancer. A critical goal in radiation therapy is to deliver optimal radiation doses to the perceived tumor while sparing the surrounding healthy tissues. Radiation oncologists often manually delineate normal and diseased structures on 3D-CT scans, a time consuming task. We present a segmentation algorithm using non-parametric snakes and principal curves that can be used in an automatic or semi-supervised fashion. It provides fast segmentation that is robust with respect to noisy edges and does not require the user to optimize a variety of parameters, unlike many segmentation algorithms. It allows multiple cues to be incorporated easily for the purposes of estimating the edge probability density. These cues, including texture, intensity and shape priors, can be used simultaneously to delineate tumors and normal anatomy, thereby increasing the robustness of the algorithm. The notion of principal curves is used to interpolate between data points in sparse areas. We compare the results using a non-parametric snake technique with a gold standard consisting of manually delineated structures for tumors as well as normal organs.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume7259
DOIs
StatePublished - 2009
EventMedical Imaging 2009 - Image Processing - Lake Buena Vista, FL, United States
Duration: Feb 8 2009Feb 10 2009

Other

OtherMedical Imaging 2009 - Image Processing
CountryUnited States
CityLake Buena Vista, FL
Period2/8/092/10/09

Fingerprint

snakes
Radiation Oncology
Oncology
Snakes
cues
Cues
Tumors
tumors
Radiotherapy
Radiation
radiation therapy
radiation
Neoplasms
Computerized tomography
anatomy
curves
organs
Dosimetry
estimating
textures

Keywords

  • Non-parametric snakes
  • Principal curves
  • Segmentation
  • Tumors

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Kalpathy-Cramer, J., Ozertem, U., Hersh, W. B., Fuss, M., & Erdogmus, D. (2009). Robust segmentation using non-parametric snakes with multiple cues for applications in radiation oncology. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 7259). [72594S] https://doi.org/10.1117/12.812712

Robust segmentation using non-parametric snakes with multiple cues for applications in radiation oncology. / Kalpathy-Cramer, Jayashree; Ozertem, Umut; Hersh, William (Bill); Fuss, Martin; Erdogmus, Deniz.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7259 2009. 72594S.

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

Kalpathy-Cramer, J, Ozertem, U, Hersh, WB, Fuss, M & Erdogmus, D 2009, Robust segmentation using non-parametric snakes with multiple cues for applications in radiation oncology. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 7259, 72594S, Medical Imaging 2009 - Image Processing, Lake Buena Vista, FL, United States, 2/8/09. https://doi.org/10.1117/12.812712
Kalpathy-Cramer J, Ozertem U, Hersh WB, Fuss M, Erdogmus D. Robust segmentation using non-parametric snakes with multiple cues for applications in radiation oncology. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7259. 2009. 72594S https://doi.org/10.1117/12.812712
Kalpathy-Cramer, Jayashree ; Ozertem, Umut ; Hersh, William (Bill) ; Fuss, Martin ; Erdogmus, Deniz. / Robust segmentation using non-parametric snakes with multiple cues for applications in radiation oncology. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7259 2009.
@inproceedings{1fddf6ef31a242c1bcc25b77b3aed753,
title = "Robust segmentation using non-parametric snakes with multiple cues for applications in radiation oncology",
abstract = "Radiation therapy is one of the most effective treatments used in the treatment of about half of all people with cancer. A critical goal in radiation therapy is to deliver optimal radiation doses to the perceived tumor while sparing the surrounding healthy tissues. Radiation oncologists often manually delineate normal and diseased structures on 3D-CT scans, a time consuming task. We present a segmentation algorithm using non-parametric snakes and principal curves that can be used in an automatic or semi-supervised fashion. It provides fast segmentation that is robust with respect to noisy edges and does not require the user to optimize a variety of parameters, unlike many segmentation algorithms. It allows multiple cues to be incorporated easily for the purposes of estimating the edge probability density. These cues, including texture, intensity and shape priors, can be used simultaneously to delineate tumors and normal anatomy, thereby increasing the robustness of the algorithm. The notion of principal curves is used to interpolate between data points in sparse areas. We compare the results using a non-parametric snake technique with a gold standard consisting of manually delineated structures for tumors as well as normal organs.",
keywords = "Non-parametric snakes, Principal curves, Segmentation, Tumors",
author = "Jayashree Kalpathy-Cramer and Umut Ozertem and Hersh, {William (Bill)} and Martin Fuss and Deniz Erdogmus",
year = "2009",
doi = "10.1117/12.812712",
language = "English (US)",
isbn = "9780819475107",
volume = "7259",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Robust segmentation using non-parametric snakes with multiple cues for applications in radiation oncology

AU - Kalpathy-Cramer, Jayashree

AU - Ozertem, Umut

AU - Hersh, William (Bill)

AU - Fuss, Martin

AU - Erdogmus, Deniz

PY - 2009

Y1 - 2009

N2 - Radiation therapy is one of the most effective treatments used in the treatment of about half of all people with cancer. A critical goal in radiation therapy is to deliver optimal radiation doses to the perceived tumor while sparing the surrounding healthy tissues. Radiation oncologists often manually delineate normal and diseased structures on 3D-CT scans, a time consuming task. We present a segmentation algorithm using non-parametric snakes and principal curves that can be used in an automatic or semi-supervised fashion. It provides fast segmentation that is robust with respect to noisy edges and does not require the user to optimize a variety of parameters, unlike many segmentation algorithms. It allows multiple cues to be incorporated easily for the purposes of estimating the edge probability density. These cues, including texture, intensity and shape priors, can be used simultaneously to delineate tumors and normal anatomy, thereby increasing the robustness of the algorithm. The notion of principal curves is used to interpolate between data points in sparse areas. We compare the results using a non-parametric snake technique with a gold standard consisting of manually delineated structures for tumors as well as normal organs.

AB - Radiation therapy is one of the most effective treatments used in the treatment of about half of all people with cancer. A critical goal in radiation therapy is to deliver optimal radiation doses to the perceived tumor while sparing the surrounding healthy tissues. Radiation oncologists often manually delineate normal and diseased structures on 3D-CT scans, a time consuming task. We present a segmentation algorithm using non-parametric snakes and principal curves that can be used in an automatic or semi-supervised fashion. It provides fast segmentation that is robust with respect to noisy edges and does not require the user to optimize a variety of parameters, unlike many segmentation algorithms. It allows multiple cues to be incorporated easily for the purposes of estimating the edge probability density. These cues, including texture, intensity and shape priors, can be used simultaneously to delineate tumors and normal anatomy, thereby increasing the robustness of the algorithm. The notion of principal curves is used to interpolate between data points in sparse areas. We compare the results using a non-parametric snake technique with a gold standard consisting of manually delineated structures for tumors as well as normal organs.

KW - Non-parametric snakes

KW - Principal curves

KW - Segmentation

KW - Tumors

UR - http://www.scopus.com/inward/record.url?scp=71649108693&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=71649108693&partnerID=8YFLogxK

U2 - 10.1117/12.812712

DO - 10.1117/12.812712

M3 - Conference contribution

SN - 9780819475107

VL - 7259

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

ER -