Localized components analysis.

Dan Alcantara, Owen Carmichael, Eric Delson, Will Harcourt-Smith, Kirsten Sterner, Stephen Frost, Rebecca Dutton, Paul Thompson, Howard Aizenstein, Oscar Lopez, James Becker, Nina Amenta

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

We introduce Localized Components Analysis (LoCA) for describing surface shape variation in an ensemble of biomedical objects using a linear subspace of spatially localized shape components. In contrast to earlier methods, LoCA optimizes explicitly for localized components and allows a flexible trade-off between localized and concise representations. Experiments comparing LoCA to a variety of competing shape representation methods on 2D and 3D shape ensembles establish the superior ability of LoCA to modulate the locality-conciseness tradeoff and generate shape components corresponding to intuitive modes of shape variation. Our formulation of locality in terms of compatibility between pairs of surface points is shown to be flexible enough to enable spatially-localized shape descriptions with attractive higher-order properties such as spatial symmetry.

Original languageEnglish (US)
Pages (from-to)519-531
Number of pages13
JournalInformation processing in medical imaging : proceedings of the ... conference
Volume20
StatePublished - 2007

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Alcantara, D., Carmichael, O., Delson, E., Harcourt-Smith, W., Sterner, K., Frost, S., ... Amenta, N. (2007). Localized components analysis. Information processing in medical imaging : proceedings of the ... conference, 20, 519-531.

Localized components analysis. / Alcantara, Dan; Carmichael, Owen; Delson, Eric; Harcourt-Smith, Will; Sterner, Kirsten; Frost, Stephen; Dutton, Rebecca; Thompson, Paul; Aizenstein, Howard; Lopez, Oscar; Becker, James; Amenta, Nina.

In: Information processing in medical imaging : proceedings of the ... conference, Vol. 20, 2007, p. 519-531.

Research output: Contribution to journalArticle

Alcantara, D, Carmichael, O, Delson, E, Harcourt-Smith, W, Sterner, K, Frost, S, Dutton, R, Thompson, P, Aizenstein, H, Lopez, O, Becker, J & Amenta, N 2007, 'Localized components analysis.', Information processing in medical imaging : proceedings of the ... conference, vol. 20, pp. 519-531.
Alcantara D, Carmichael O, Delson E, Harcourt-Smith W, Sterner K, Frost S et al. Localized components analysis. Information processing in medical imaging : proceedings of the ... conference. 2007;20:519-531.
Alcantara, Dan ; Carmichael, Owen ; Delson, Eric ; Harcourt-Smith, Will ; Sterner, Kirsten ; Frost, Stephen ; Dutton, Rebecca ; Thompson, Paul ; Aizenstein, Howard ; Lopez, Oscar ; Becker, James ; Amenta, Nina. / Localized components analysis. In: Information processing in medical imaging : proceedings of the ... conference. 2007 ; Vol. 20. pp. 519-531.
@article{de3ba4c60ba740db99407cea4fd92f4e,
title = "Localized components analysis.",
abstract = "We introduce Localized Components Analysis (LoCA) for describing surface shape variation in an ensemble of biomedical objects using a linear subspace of spatially localized shape components. In contrast to earlier methods, LoCA optimizes explicitly for localized components and allows a flexible trade-off between localized and concise representations. Experiments comparing LoCA to a variety of competing shape representation methods on 2D and 3D shape ensembles establish the superior ability of LoCA to modulate the locality-conciseness tradeoff and generate shape components corresponding to intuitive modes of shape variation. Our formulation of locality in terms of compatibility between pairs of surface points is shown to be flexible enough to enable spatially-localized shape descriptions with attractive higher-order properties such as spatial symmetry.",
author = "Dan Alcantara and Owen Carmichael and Eric Delson and Will Harcourt-Smith and Kirsten Sterner and Stephen Frost and Rebecca Dutton and Paul Thompson and Howard Aizenstein and Oscar Lopez and James Becker and Nina Amenta",
year = "2007",
language = "English (US)",
volume = "20",
pages = "519--531",
journal = "Information processing in medical imaging : proceedings of the ... conference",
issn = "1011-2499",
publisher = "Springer Verlag",

}

TY - JOUR

T1 - Localized components analysis.

AU - Alcantara, Dan

AU - Carmichael, Owen

AU - Delson, Eric

AU - Harcourt-Smith, Will

AU - Sterner, Kirsten

AU - Frost, Stephen

AU - Dutton, Rebecca

AU - Thompson, Paul

AU - Aizenstein, Howard

AU - Lopez, Oscar

AU - Becker, James

AU - Amenta, Nina

PY - 2007

Y1 - 2007

N2 - We introduce Localized Components Analysis (LoCA) for describing surface shape variation in an ensemble of biomedical objects using a linear subspace of spatially localized shape components. In contrast to earlier methods, LoCA optimizes explicitly for localized components and allows a flexible trade-off between localized and concise representations. Experiments comparing LoCA to a variety of competing shape representation methods on 2D and 3D shape ensembles establish the superior ability of LoCA to modulate the locality-conciseness tradeoff and generate shape components corresponding to intuitive modes of shape variation. Our formulation of locality in terms of compatibility between pairs of surface points is shown to be flexible enough to enable spatially-localized shape descriptions with attractive higher-order properties such as spatial symmetry.

AB - We introduce Localized Components Analysis (LoCA) for describing surface shape variation in an ensemble of biomedical objects using a linear subspace of spatially localized shape components. In contrast to earlier methods, LoCA optimizes explicitly for localized components and allows a flexible trade-off between localized and concise representations. Experiments comparing LoCA to a variety of competing shape representation methods on 2D and 3D shape ensembles establish the superior ability of LoCA to modulate the locality-conciseness tradeoff and generate shape components corresponding to intuitive modes of shape variation. Our formulation of locality in terms of compatibility between pairs of surface points is shown to be flexible enough to enable spatially-localized shape descriptions with attractive higher-order properties such as spatial symmetry.

UR - http://www.scopus.com/inward/record.url?scp=34548453163&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548453163&partnerID=8YFLogxK

M3 - Article

C2 - 17633726

AN - SCOPUS:34548453163

VL - 20

SP - 519

EP - 531

JO - Information processing in medical imaging : proceedings of the ... conference

JF - Information processing in medical imaging : proceedings of the ... conference

SN - 1011-2499

ER -