A parallel cellular automata with label priors for interactive brain tumor segmentation

Edward Kim, Tian Shen, Sharon Xiaolei Huang

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

13 Citations (Scopus)

Abstract

We present a novel method for 3D brain tumor volume segmentation based on a parallel cellular automata framework. Our method incorporates prior label knowledge gathered from user seed information to influence the cellular automata decision rules. Our proposed method is able to segment brain tumor volumes quickly and accurately using any number of label classifications. Exploiting the inherent parallelism of our algorithm, we adopt this method to the Graphics Processing Unit (GPU). Additionally, we introduce the concept of individual label strength maps to visualize the improvements of our method. As we demonstrate in our quantitative and qualitative results, the key benefits of our system are accuracy, robustness to complex structures, and speed. We compute segmentations nearly 45 faster than conventional CPU methods, enabling user feedback at interactive rates.

Original languageEnglish (US)
Title of host publicationProceedings of the 23rd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2010
Pages232-237
Number of pages6
DOIs
StatePublished - Dec 1 2010
Event23rd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2010 - Perth, Australia
Duration: Oct 12 2010Oct 15 2010

Publication series

NameProceedings - IEEE Symposium on Computer-Based Medical Systems
ISSN (Print)1063-7125

Conference

Conference23rd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2010
CountryAustralia
CityPerth
Period10/12/1010/15/10

Fingerprint

Cellular automata
Brain Neoplasms
Labels
Tumors
Brain
Tumor Burden
Program processors
Seed
Feedback
Seeds

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging
  • Computer Science Applications

Cite this

Kim, E., Shen, T., & Huang, S. X. (2010). A parallel cellular automata with label priors for interactive brain tumor segmentation. In Proceedings of the 23rd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2010 (pp. 232-237). [6042647] (Proceedings - IEEE Symposium on Computer-Based Medical Systems). https://doi.org/10.1109/CBMS.2010.6042647
Kim, Edward ; Shen, Tian ; Huang, Sharon Xiaolei. / A parallel cellular automata with label priors for interactive brain tumor segmentation. Proceedings of the 23rd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2010. 2010. pp. 232-237 (Proceedings - IEEE Symposium on Computer-Based Medical Systems).
@inproceedings{6f53eee41b7f43b3ac9b96e8d0888db5,
title = "A parallel cellular automata with label priors for interactive brain tumor segmentation",
abstract = "We present a novel method for 3D brain tumor volume segmentation based on a parallel cellular automata framework. Our method incorporates prior label knowledge gathered from user seed information to influence the cellular automata decision rules. Our proposed method is able to segment brain tumor volumes quickly and accurately using any number of label classifications. Exploiting the inherent parallelism of our algorithm, we adopt this method to the Graphics Processing Unit (GPU). Additionally, we introduce the concept of individual label strength maps to visualize the improvements of our method. As we demonstrate in our quantitative and qualitative results, the key benefits of our system are accuracy, robustness to complex structures, and speed. We compute segmentations nearly 45 faster than conventional CPU methods, enabling user feedback at interactive rates.",
author = "Edward Kim and Tian Shen and Huang, {Sharon Xiaolei}",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/CBMS.2010.6042647",
language = "English (US)",
isbn = "9781424491667",
series = "Proceedings - IEEE Symposium on Computer-Based Medical Systems",
pages = "232--237",
booktitle = "Proceedings of the 23rd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2010",

}

Kim, E, Shen, T & Huang, SX 2010, A parallel cellular automata with label priors for interactive brain tumor segmentation. in Proceedings of the 23rd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2010., 6042647, Proceedings - IEEE Symposium on Computer-Based Medical Systems, pp. 232-237, 23rd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2010, Perth, Australia, 10/12/10. https://doi.org/10.1109/CBMS.2010.6042647

A parallel cellular automata with label priors for interactive brain tumor segmentation. / Kim, Edward; Shen, Tian; Huang, Sharon Xiaolei.

Proceedings of the 23rd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2010. 2010. p. 232-237 6042647 (Proceedings - IEEE Symposium on Computer-Based Medical Systems).

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

TY - GEN

T1 - A parallel cellular automata with label priors for interactive brain tumor segmentation

AU - Kim, Edward

AU - Shen, Tian

AU - Huang, Sharon Xiaolei

PY - 2010/12/1

Y1 - 2010/12/1

N2 - We present a novel method for 3D brain tumor volume segmentation based on a parallel cellular automata framework. Our method incorporates prior label knowledge gathered from user seed information to influence the cellular automata decision rules. Our proposed method is able to segment brain tumor volumes quickly and accurately using any number of label classifications. Exploiting the inherent parallelism of our algorithm, we adopt this method to the Graphics Processing Unit (GPU). Additionally, we introduce the concept of individual label strength maps to visualize the improvements of our method. As we demonstrate in our quantitative and qualitative results, the key benefits of our system are accuracy, robustness to complex structures, and speed. We compute segmentations nearly 45 faster than conventional CPU methods, enabling user feedback at interactive rates.

AB - We present a novel method for 3D brain tumor volume segmentation based on a parallel cellular automata framework. Our method incorporates prior label knowledge gathered from user seed information to influence the cellular automata decision rules. Our proposed method is able to segment brain tumor volumes quickly and accurately using any number of label classifications. Exploiting the inherent parallelism of our algorithm, we adopt this method to the Graphics Processing Unit (GPU). Additionally, we introduce the concept of individual label strength maps to visualize the improvements of our method. As we demonstrate in our quantitative and qualitative results, the key benefits of our system are accuracy, robustness to complex structures, and speed. We compute segmentations nearly 45 faster than conventional CPU methods, enabling user feedback at interactive rates.

UR - http://www.scopus.com/inward/record.url?scp=80055088217&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80055088217&partnerID=8YFLogxK

U2 - 10.1109/CBMS.2010.6042647

DO - 10.1109/CBMS.2010.6042647

M3 - Conference contribution

AN - SCOPUS:80055088217

SN - 9781424491667

T3 - Proceedings - IEEE Symposium on Computer-Based Medical Systems

SP - 232

EP - 237

BT - Proceedings of the 23rd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2010

ER -

Kim E, Shen T, Huang SX. A parallel cellular automata with label priors for interactive brain tumor segmentation. In Proceedings of the 23rd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2010. 2010. p. 232-237. 6042647. (Proceedings - IEEE Symposium on Computer-Based Medical Systems). https://doi.org/10.1109/CBMS.2010.6042647