Unified and contrasting cuts in multiple graphs

Application to medical imaging segmentation

Chia Tung Kuo, Xiang Wang, Peter Walker, Owen Carmichael, Jieping Ye, Ian Davidson

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

10 Citations (Scopus)

Abstract

The analysis of data represented as graphs is common having wide scale applications from social networks to medical imaging. A popular analysis is to cut the graph so that the disjoint subgraphs can represent communities (for social network) or background and foreground cognitive activity (for medical imaging). An emerging setting is when multiple data sets (graphs) exist which opens up the opportunity for many new questions. In this paper we study two such questions: i) For a collection of graphs find a single cut that is good for all the graphs and ii) For two collections of graphs find a single cut that is good for one collection but poor for the other. We show that existing formulations of multiview, consensus and alternative clustering cannot address these questions and instead we provide novel formulations in the spectral clustering framework. We evaluate our approaches on functional magnetic resonance imaging (fMRI) data to address questions such as: "What common cognitive network does this group of individuals have?" and "What are the differences in the cognitive networks for these two groups?" We obtain useful results without the need for strong domain knowledge.

Original languageEnglish (US)
Title of host publicationProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages617-626
Number of pages10
Volume2015-August
ISBN (Print)9781450336642
DOIs
StatePublished - Aug 10 2015
Event21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2015 - Sydney, Australia
Duration: Aug 10 2015Aug 13 2015

Other

Other21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2015
CountryAustralia
CitySydney
Period8/10/158/13/15

Fingerprint

Medical imaging
Magnetic Resonance Imaging

Keywords

  • Application
  • FMRI
  • Graph cuts

ASJC Scopus subject areas

  • Software
  • Information Systems

Cite this

Kuo, C. T., Wang, X., Walker, P., Carmichael, O., Ye, J., & Davidson, I. (2015). Unified and contrasting cuts in multiple graphs: Application to medical imaging segmentation. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Vol. 2015-August, pp. 617-626). Association for Computing Machinery. https://doi.org/10.1145/2783258.2783318

Unified and contrasting cuts in multiple graphs : Application to medical imaging segmentation. / Kuo, Chia Tung; Wang, Xiang; Walker, Peter; Carmichael, Owen; Ye, Jieping; Davidson, Ian.

Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. 2015-August Association for Computing Machinery, 2015. p. 617-626.

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

Kuo, CT, Wang, X, Walker, P, Carmichael, O, Ye, J & Davidson, I 2015, Unified and contrasting cuts in multiple graphs: Application to medical imaging segmentation. in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. vol. 2015-August, Association for Computing Machinery, pp. 617-626, 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2015, Sydney, Australia, 8/10/15. https://doi.org/10.1145/2783258.2783318
Kuo CT, Wang X, Walker P, Carmichael O, Ye J, Davidson I. Unified and contrasting cuts in multiple graphs: Application to medical imaging segmentation. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. 2015-August. Association for Computing Machinery. 2015. p. 617-626 https://doi.org/10.1145/2783258.2783318
Kuo, Chia Tung ; Wang, Xiang ; Walker, Peter ; Carmichael, Owen ; Ye, Jieping ; Davidson, Ian. / Unified and contrasting cuts in multiple graphs : Application to medical imaging segmentation. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. 2015-August Association for Computing Machinery, 2015. pp. 617-626
@inproceedings{d4ad1c5fdb9c43cfb33bec5b01f0b264,
title = "Unified and contrasting cuts in multiple graphs: Application to medical imaging segmentation",
abstract = "The analysis of data represented as graphs is common having wide scale applications from social networks to medical imaging. A popular analysis is to cut the graph so that the disjoint subgraphs can represent communities (for social network) or background and foreground cognitive activity (for medical imaging). An emerging setting is when multiple data sets (graphs) exist which opens up the opportunity for many new questions. In this paper we study two such questions: i) For a collection of graphs find a single cut that is good for all the graphs and ii) For two collections of graphs find a single cut that is good for one collection but poor for the other. We show that existing formulations of multiview, consensus and alternative clustering cannot address these questions and instead we provide novel formulations in the spectral clustering framework. We evaluate our approaches on functional magnetic resonance imaging (fMRI) data to address questions such as: {"}What common cognitive network does this group of individuals have?{"} and {"}What are the differences in the cognitive networks for these two groups?{"} We obtain useful results without the need for strong domain knowledge.",
keywords = "Application, FMRI, Graph cuts",
author = "Kuo, {Chia Tung} and Xiang Wang and Peter Walker and Owen Carmichael and Jieping Ye and Ian Davidson",
year = "2015",
month = "8",
day = "10",
doi = "10.1145/2783258.2783318",
language = "English (US)",
isbn = "9781450336642",
volume = "2015-August",
pages = "617--626",
booktitle = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Unified and contrasting cuts in multiple graphs

T2 - Application to medical imaging segmentation

AU - Kuo, Chia Tung

AU - Wang, Xiang

AU - Walker, Peter

AU - Carmichael, Owen

AU - Ye, Jieping

AU - Davidson, Ian

PY - 2015/8/10

Y1 - 2015/8/10

N2 - The analysis of data represented as graphs is common having wide scale applications from social networks to medical imaging. A popular analysis is to cut the graph so that the disjoint subgraphs can represent communities (for social network) or background and foreground cognitive activity (for medical imaging). An emerging setting is when multiple data sets (graphs) exist which opens up the opportunity for many new questions. In this paper we study two such questions: i) For a collection of graphs find a single cut that is good for all the graphs and ii) For two collections of graphs find a single cut that is good for one collection but poor for the other. We show that existing formulations of multiview, consensus and alternative clustering cannot address these questions and instead we provide novel formulations in the spectral clustering framework. We evaluate our approaches on functional magnetic resonance imaging (fMRI) data to address questions such as: "What common cognitive network does this group of individuals have?" and "What are the differences in the cognitive networks for these two groups?" We obtain useful results without the need for strong domain knowledge.

AB - The analysis of data represented as graphs is common having wide scale applications from social networks to medical imaging. A popular analysis is to cut the graph so that the disjoint subgraphs can represent communities (for social network) or background and foreground cognitive activity (for medical imaging). An emerging setting is when multiple data sets (graphs) exist which opens up the opportunity for many new questions. In this paper we study two such questions: i) For a collection of graphs find a single cut that is good for all the graphs and ii) For two collections of graphs find a single cut that is good for one collection but poor for the other. We show that existing formulations of multiview, consensus and alternative clustering cannot address these questions and instead we provide novel formulations in the spectral clustering framework. We evaluate our approaches on functional magnetic resonance imaging (fMRI) data to address questions such as: "What common cognitive network does this group of individuals have?" and "What are the differences in the cognitive networks for these two groups?" We obtain useful results without the need for strong domain knowledge.

KW - Application

KW - FMRI

KW - Graph cuts

UR - http://www.scopus.com/inward/record.url?scp=84954155242&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84954155242&partnerID=8YFLogxK

U2 - 10.1145/2783258.2783318

DO - 10.1145/2783258.2783318

M3 - Conference contribution

SN - 9781450336642

VL - 2015-August

SP - 617

EP - 626

BT - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery

ER -