Iterative-cuts: longitudinal and scale-invariant segmentation via user-defined templates for rectosigmoid colon in gynecological brachytherapy

Tobias Lüddemann, Jan Egger

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Among all types of cancer, gynecological malignancies belong to the fourth most frequent type of cancer among women. In addition to chemotherapy and external beam radiation, brachytherapy is the standard procedure for the treatment of these malignancies. In the progress of treatment planning, localization of the tumor as the target volume and adjacent organs of risks by segmentation is crucial to accomplish an optimal radiation distribution to the tumor while simultaneously preserving healthy tissue. Segmentation is performed manually and represents a time-consuming task in clinical daily routine. This study focuses on the segmentation of the rectum/sigmoid colon as an organ-at-risk in gynecological brachytherapy. The proposed segmentation method uses an interactive, graph-based segmentation scheme with a user-defined template. The scheme creates a directed two-dimensional graph, followed by the minimal cost closed set computation on the graph, resulting in an outlining of the rectum. The graph's outline is dynamically adapted to the last calculated cut. Evaluation was performed by comparing manual segmentations of the rectum/sigmoid colon to results achieved with the proposed method. The comparison of the algorithmic to manual result yielded a dice similarity coefficient value of [Formula: see text], in comparison to [Formula: see text] for the comparison of two manual segmentations by the same physician. Utilizing the proposed methodology resulted in a median time of [Formula: see text], compared to 300 s needed for pure manual segmentation.

Original languageEnglish
Pages (from-to)024004
JournalJournal of medical imaging (Bellingham, Wash.)
Volume3
Issue number2
DOIs
Publication statusPublished - Apr 2016

Fingerprint

Brachytherapy
Colon
Rectum
Neoplasms
Sigmoid Colon
Radiation
Organs at Risk
Organ Size
Physicians
Costs and Cost Analysis
Drug Therapy
Therapeutics

Keywords

  • Journal Article

Cite this

Iterative-cuts : longitudinal and scale-invariant segmentation via user-defined templates for rectosigmoid colon in gynecological brachytherapy. / Lüddemann, Tobias; Egger, Jan.

In: Journal of medical imaging (Bellingham, Wash.), Vol. 3, No. 2, 04.2016, p. 024004.

Research output: Contribution to journalArticleResearchpeer-review

@article{1e49ef8bc0e14fc9b0003a64b1f4b35b,
title = "Iterative-cuts: longitudinal and scale-invariant segmentation via user-defined templates for rectosigmoid colon in gynecological brachytherapy",
abstract = "Among all types of cancer, gynecological malignancies belong to the fourth most frequent type of cancer among women. In addition to chemotherapy and external beam radiation, brachytherapy is the standard procedure for the treatment of these malignancies. In the progress of treatment planning, localization of the tumor as the target volume and adjacent organs of risks by segmentation is crucial to accomplish an optimal radiation distribution to the tumor while simultaneously preserving healthy tissue. Segmentation is performed manually and represents a time-consuming task in clinical daily routine. This study focuses on the segmentation of the rectum/sigmoid colon as an organ-at-risk in gynecological brachytherapy. The proposed segmentation method uses an interactive, graph-based segmentation scheme with a user-defined template. The scheme creates a directed two-dimensional graph, followed by the minimal cost closed set computation on the graph, resulting in an outlining of the rectum. The graph's outline is dynamically adapted to the last calculated cut. Evaluation was performed by comparing manual segmentations of the rectum/sigmoid colon to results achieved with the proposed method. The comparison of the algorithmic to manual result yielded a dice similarity coefficient value of [Formula: see text], in comparison to [Formula: see text] for the comparison of two manual segmentations by the same physician. Utilizing the proposed methodology resulted in a median time of [Formula: see text], compared to 300 s needed for pure manual segmentation.",
keywords = "Journal Article",
author = "Tobias L{\"u}ddemann and Jan Egger",
year = "2016",
month = "4",
doi = "10.1117/1.JMI.3.2.024004",
language = "English",
volume = "3",
pages = "024004",
journal = "Journal of medical imaging (Bellingham, Wash.)",
issn = "2329-4302",
publisher = "SPIE",
number = "2",

}

TY - JOUR

T1 - Iterative-cuts

T2 - longitudinal and scale-invariant segmentation via user-defined templates for rectosigmoid colon in gynecological brachytherapy

AU - Lüddemann, Tobias

AU - Egger, Jan

PY - 2016/4

Y1 - 2016/4

N2 - Among all types of cancer, gynecological malignancies belong to the fourth most frequent type of cancer among women. In addition to chemotherapy and external beam radiation, brachytherapy is the standard procedure for the treatment of these malignancies. In the progress of treatment planning, localization of the tumor as the target volume and adjacent organs of risks by segmentation is crucial to accomplish an optimal radiation distribution to the tumor while simultaneously preserving healthy tissue. Segmentation is performed manually and represents a time-consuming task in clinical daily routine. This study focuses on the segmentation of the rectum/sigmoid colon as an organ-at-risk in gynecological brachytherapy. The proposed segmentation method uses an interactive, graph-based segmentation scheme with a user-defined template. The scheme creates a directed two-dimensional graph, followed by the minimal cost closed set computation on the graph, resulting in an outlining of the rectum. The graph's outline is dynamically adapted to the last calculated cut. Evaluation was performed by comparing manual segmentations of the rectum/sigmoid colon to results achieved with the proposed method. The comparison of the algorithmic to manual result yielded a dice similarity coefficient value of [Formula: see text], in comparison to [Formula: see text] for the comparison of two manual segmentations by the same physician. Utilizing the proposed methodology resulted in a median time of [Formula: see text], compared to 300 s needed for pure manual segmentation.

AB - Among all types of cancer, gynecological malignancies belong to the fourth most frequent type of cancer among women. In addition to chemotherapy and external beam radiation, brachytherapy is the standard procedure for the treatment of these malignancies. In the progress of treatment planning, localization of the tumor as the target volume and adjacent organs of risks by segmentation is crucial to accomplish an optimal radiation distribution to the tumor while simultaneously preserving healthy tissue. Segmentation is performed manually and represents a time-consuming task in clinical daily routine. This study focuses on the segmentation of the rectum/sigmoid colon as an organ-at-risk in gynecological brachytherapy. The proposed segmentation method uses an interactive, graph-based segmentation scheme with a user-defined template. The scheme creates a directed two-dimensional graph, followed by the minimal cost closed set computation on the graph, resulting in an outlining of the rectum. The graph's outline is dynamically adapted to the last calculated cut. Evaluation was performed by comparing manual segmentations of the rectum/sigmoid colon to results achieved with the proposed method. The comparison of the algorithmic to manual result yielded a dice similarity coefficient value of [Formula: see text], in comparison to [Formula: see text] for the comparison of two manual segmentations by the same physician. Utilizing the proposed methodology resulted in a median time of [Formula: see text], compared to 300 s needed for pure manual segmentation.

KW - Journal Article

U2 - 10.1117/1.JMI.3.2.024004

DO - 10.1117/1.JMI.3.2.024004

M3 - Article

VL - 3

SP - 024004

JO - Journal of medical imaging (Bellingham, Wash.)

JF - Journal of medical imaging (Bellingham, Wash.)

SN - 2329-4302

IS - 2

ER -