A multidimensional data visualization and clustering method: Consensus similarity mapping

Vishwa S. Parekh; Michael Jacobs

doi:10.1109/ISBI.2016.7493297

A multidimensional data visualization and clustering method: Consensus similarity mapping

Vishwa S. Parekh, Michael Jacobs

School of Medicine

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

Multiparametric Magnetic Resonance Imaging (MRI) produces large amounts of high dimensional data for radiologists to read. Currently, radiologists integrate multiparametric MRI data visually to identify meaningful structures within the data. In this paper, we present a novel visualization and clustering technique called «Consensus Similarity Mapping (CSM)» for integration of multidimensional radiological data. The CSM algorithm computes an ensemble of stable clustering results obtained from multiple runs of the k-means algorithm. The CSM algorithm uses a unique method called cluster stability index (CSI) to identify the stable clustering configurations required to create the k-means ensemble. The CSM algorithm transforms the stable clustering ensemble into a matrix of pairwise similarities, which, uncovers the intrinsic classes within the high dimensional input data. We demonstrate the performance of CSM on well-known synthetic datasets as well as multiparametric magnetic resonance imaging (MRI) data.

Original language	English (US)
Title of host publication	2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings
Publisher	IEEE Computer Society
Pages	420-423
Number of pages	4
Volume	2016-June
ISBN (Electronic)	9781479923502
DOIs	https://doi.org/10.1109/ISBI.2016.7493297
State	Published - Jun 15 2016
Event	2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Prague, Czech Republic Duration: Apr 13 2016 → Apr 16 2016

Other

Other	2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016
Country/Territory	Czech Republic
City	Prague
Period	4/13/16 → 4/16/16

Keywords

clustering
evidence accumulation
multiparametric MRI
nonlinear dimensionality reduction
segmentation

ASJC Scopus subject areas

Biomedical Engineering
Radiology Nuclear Medicine and imaging

Access to Document

10.1109/ISBI.2016.7493297

Cite this

A multidimensional data visualization and clustering method: Consensus similarity mapping. / Parekh, Vishwa S.; Jacobs, Michael.
2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings. Vol. 2016-June IEEE Computer Society, 2016. p. 420-423 7493297.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Parekh, VS & Jacobs, M 2016, A multidimensional data visualization and clustering method: Consensus similarity mapping. in 2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings. vol. 2016-June, 7493297, IEEE Computer Society, pp. 420-423, 2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016, Prague, Czech Republic, 4/13/16. https://doi.org/10.1109/ISBI.2016.7493297

@inproceedings{d465aa479df448e3b3e918e948466c3e,

title = "A multidimensional data visualization and clustering method: Consensus similarity mapping",

abstract = "Multiparametric Magnetic Resonance Imaging (MRI) produces large amounts of high dimensional data for radiologists to read. Currently, radiologists integrate multiparametric MRI data visually to identify meaningful structures within the data. In this paper, we present a novel visualization and clustering technique called «Consensus Similarity Mapping (CSM)» for integration of multidimensional radiological data. The CSM algorithm computes an ensemble of stable clustering results obtained from multiple runs of the k-means algorithm. The CSM algorithm uses a unique method called cluster stability index (CSI) to identify the stable clustering configurations required to create the k-means ensemble. The CSM algorithm transforms the stable clustering ensemble into a matrix of pairwise similarities, which, uncovers the intrinsic classes within the high dimensional input data. We demonstrate the performance of CSM on well-known synthetic datasets as well as multiparametric magnetic resonance imaging (MRI) data.",

keywords = "clustering, evidence accumulation, multiparametric MRI, nonlinear dimensionality reduction, segmentation",

author = "Parekh, {Vishwa S.} and Michael Jacobs",

year = "2016",

month = jun,

day = "15",

doi = "10.1109/ISBI.2016.7493297",

language = "English (US)",

volume = "2016-June",

pages = "420--423",

booktitle = "2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings",

publisher = "IEEE Computer Society",

note = "2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 ; Conference date: 13-04-2016 Through 16-04-2016",

}

TY - GEN

T1 - A multidimensional data visualization and clustering method

T2 - 2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016

AU - Parekh, Vishwa S.

AU - Jacobs, Michael

PY - 2016/6/15

Y1 - 2016/6/15

N2 - Multiparametric Magnetic Resonance Imaging (MRI) produces large amounts of high dimensional data for radiologists to read. Currently, radiologists integrate multiparametric MRI data visually to identify meaningful structures within the data. In this paper, we present a novel visualization and clustering technique called «Consensus Similarity Mapping (CSM)» for integration of multidimensional radiological data. The CSM algorithm computes an ensemble of stable clustering results obtained from multiple runs of the k-means algorithm. The CSM algorithm uses a unique method called cluster stability index (CSI) to identify the stable clustering configurations required to create the k-means ensemble. The CSM algorithm transforms the stable clustering ensemble into a matrix of pairwise similarities, which, uncovers the intrinsic classes within the high dimensional input data. We demonstrate the performance of CSM on well-known synthetic datasets as well as multiparametric magnetic resonance imaging (MRI) data.

AB - Multiparametric Magnetic Resonance Imaging (MRI) produces large amounts of high dimensional data for radiologists to read. Currently, radiologists integrate multiparametric MRI data visually to identify meaningful structures within the data. In this paper, we present a novel visualization and clustering technique called «Consensus Similarity Mapping (CSM)» for integration of multidimensional radiological data. The CSM algorithm computes an ensemble of stable clustering results obtained from multiple runs of the k-means algorithm. The CSM algorithm uses a unique method called cluster stability index (CSI) to identify the stable clustering configurations required to create the k-means ensemble. The CSM algorithm transforms the stable clustering ensemble into a matrix of pairwise similarities, which, uncovers the intrinsic classes within the high dimensional input data. We demonstrate the performance of CSM on well-known synthetic datasets as well as multiparametric magnetic resonance imaging (MRI) data.

KW - clustering

KW - evidence accumulation

KW - multiparametric MRI

KW - nonlinear dimensionality reduction

KW - segmentation

UR - http://www.scopus.com/inward/record.url?scp=84978374588&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84978374588&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2016.7493297

DO - 10.1109/ISBI.2016.7493297

M3 - Conference contribution

AN - SCOPUS:84978374588

VL - 2016-June

SP - 420

EP - 423

BT - 2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings

PB - IEEE Computer Society

Y2 - 13 April 2016 through 16 April 2016

ER -

A multidimensional data visualization and clustering method: Consensus similarity mapping

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this