Lung Tumor Segmentation Using Electric Flow Lines for Graph Cuts

Christian Hollensen; George  Cannon; Donald  Cannon; Søren  Bentzen; Rasmus Larsen

doi:10.1007/978-3-642-31298-4_25

Lung Tumor Segmentation Using Electric Flow Lines for Graph Cuts

Christian Hollensen, George Cannon, Donald Cannon, Søren Bentzen, Rasmus Larsen

University of Wisconsin-Madison

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

480 Downloads (Pure)

Abstract

Lung cancer is the most common cause of cancer-related death. A common treatment is radiotherapy where the lung tumors are irradiated with ionizing radiation. The treatment is typically fractionated, i.e. spread out over time, allowing healthy tissue to recover between treatments and allowing tumor cells to be hit in their most sensitive phase. Changes in tumors over the course of treatment allows for an adaptation of the radiotherapy plan based on 3D computer tomography imaging. This paper introduces a method for segmentation of lung tumors on consecutive computed tomography images. These images are normally only used for correction of movements. The method uses graphs based on electric flow lines. The method offers several advantages when trying to replicate manual segmentations. The method gave a dice coefficient of 0.85 and performed better than level set methods and deformable registration.

Original language	English
Title of host publication	Image Analysis and Recognition : 9th International Conference, ICIAR 2012 Aveiro, Portugal, June 25-27, 2012 Proceedings, Part II
Publisher	Springer
Publication date	2012
Pages	206-213
ISBN (Print)	978-3-642-31297-7
ISBN (Electronic)	978-3-642-31298-4
DOIs	https://doi.org/10.1007/978-3-642-31298-4_25
Publication status	Published - 2012
Event	International Conference on Image Analysis and Recognition, ICIAR 2012 - Aveiro, Portugal Duration: 25 Jun 2012 → 27 Jun 2012 http://www.iciar.uwaterloo.ca/iciar12/

Conference

Conference	International Conference on Image Analysis and Recognition, ICIAR 2012
Country/Territory	Portugal
City	Aveiro
Period	25/06/2012 → 27/06/2012
Internet address	http://www.iciar.uwaterloo.ca/iciar12/

Series	Lecture Notes in Computer Science
Number	7325
ISSN	0302-9743

Keywords

Electric flow line
Segmentation
Lung tumor
Graph cut

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-642-31298-4_25

ICIAR2012

OpenUrl availability

Full text

Cite this

@inproceedings{095e9230244f4550a53d2fb2742895b1,

title = "Lung Tumor Segmentation Using Electric Flow Lines for Graph Cuts",

abstract = "Lung cancer is the most common cause of cancer-related death. A common treatment is radiotherapy where the lung tumors are irradiated with ionizing radiation. The treatment is typically fractionated, i.e. spread out over time, allowing healthy tissue to recover between treatments and allowing tumor cells to be hit in their most sensitive phase. Changes in tumors over the course of treatment allows for an adaptation of the radiotherapy plan based on 3D computer tomography imaging. This paper introduces a method for segmentation of lung tumors on consecutive computed tomography images. These images are normally only used for correction of movements. The method uses graphs based on electric flow lines. The method offers several advantages when trying to replicate manual segmentations. The method gave a dice coefficient of 0.85 and performed better than level set methods and deformable registration. ",

keywords = "Electric flow line, Segmentation, Lung tumor, Graph cut",

author = "Christian Hollensen and George Cannon and Donald Cannon and S{\o}ren Bentzen and Rasmus Larsen",

year = "2012",

doi = "10.1007/978-3-642-31298-4_25",

language = "English",

isbn = "978-3-642-31297-7",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

number = "7325",

pages = "206--213",

booktitle = "Image Analysis and Recognition",

note = "International Conference on Image Analysis and Recognition, ICIAR 2012 ; Conference date: 25-06-2012 Through 27-06-2012",

url = "http://www.iciar.uwaterloo.ca/iciar12/",

}

Hollensen, C, Cannon, G, Cannon, D, Bentzen, S & Larsen, R 2012, Lung Tumor Segmentation Using Electric Flow Lines for Graph Cuts. in Image Analysis and Recognition: 9th International Conference, ICIAR 2012 Aveiro, Portugal, June 25-27, 2012 Proceedings, Part II. Springer, Lecture Notes in Computer Science, no. 7325, pp. 206-213, International Conference on Image Analysis and Recognition, ICIAR 2012, Aveiro, Portugal, 25/06/2012. https://doi.org/10.1007/978-3-642-31298-4_25

Lung Tumor Segmentation Using Electric Flow Lines for Graph Cuts. / Hollensen, Christian; Cannon, George ; Cannon, Donald et al.
Image Analysis and Recognition: 9th International Conference, ICIAR 2012 Aveiro, Portugal, June 25-27, 2012 Proceedings, Part II. Springer, 2012. p. 206-213 (Lecture Notes in Computer Science; No. 7325).

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

TY - GEN

T1 - Lung Tumor Segmentation Using Electric Flow Lines for Graph Cuts

AU - Hollensen, Christian

AU - Cannon, George

AU - Cannon, Donald

AU - Bentzen, Søren

AU - Larsen, Rasmus

PY - 2012

Y1 - 2012

N2 - Lung cancer is the most common cause of cancer-related death. A common treatment is radiotherapy where the lung tumors are irradiated with ionizing radiation. The treatment is typically fractionated, i.e. spread out over time, allowing healthy tissue to recover between treatments and allowing tumor cells to be hit in their most sensitive phase. Changes in tumors over the course of treatment allows for an adaptation of the radiotherapy plan based on 3D computer tomography imaging. This paper introduces a method for segmentation of lung tumors on consecutive computed tomography images. These images are normally only used for correction of movements. The method uses graphs based on electric flow lines. The method offers several advantages when trying to replicate manual segmentations. The method gave a dice coefficient of 0.85 and performed better than level set methods and deformable registration.

AB - Lung cancer is the most common cause of cancer-related death. A common treatment is radiotherapy where the lung tumors are irradiated with ionizing radiation. The treatment is typically fractionated, i.e. spread out over time, allowing healthy tissue to recover between treatments and allowing tumor cells to be hit in their most sensitive phase. Changes in tumors over the course of treatment allows for an adaptation of the radiotherapy plan based on 3D computer tomography imaging. This paper introduces a method for segmentation of lung tumors on consecutive computed tomography images. These images are normally only used for correction of movements. The method uses graphs based on electric flow lines. The method offers several advantages when trying to replicate manual segmentations. The method gave a dice coefficient of 0.85 and performed better than level set methods and deformable registration.

KW - Electric flow line

KW - Segmentation

KW - Lung tumor

KW - Graph cut

U2 - 10.1007/978-3-642-31298-4_25

DO - 10.1007/978-3-642-31298-4_25

M3 - Article in proceedings

SN - 978-3-642-31297-7

T3 - Lecture Notes in Computer Science

SP - 206

EP - 213

BT - Image Analysis and Recognition

PB - Springer

T2 - International Conference on Image Analysis and Recognition, ICIAR 2012

Y2 - 25 June 2012 through 27 June 2012

ER -

Lung Tumor Segmentation Using Electric Flow Lines for Graph Cuts

Abstract

Conference

Keywords

UN SDGs

Access to Document

OpenUrl availability

Fingerprint

Cite this