Point-Based Statistical Shape Models with Probabilistic Correspondences and Affine EM-ICP

Heike Hufnagel; Xavier Pennec; Jan Ehrhardt; Heinz Handels; Nicholas Ayache

doi:10.1007/978-3-540-71091-2_87

Point-Based Statistical Shape Models with Probabilistic Correspondences and Affine EM-ICP

Heike Hufnagel, Xavier Pennec, Jan Ehrhardt, Heinz Handels, Nicholas Ayache

Institute of Medical Informatics

INRIA Sophia Antipolis

Abstract

A fundamental problem when computing statistical shape models (SSMs) is the determination of correspondences between the instances. Often, homologies between points that represent the surfaces are assumed which might lead to imprecise mean shape and variation results. We present a novel algorithm based on the affine Expectation Maximization - Iterative Closest Point (EM-ICP) registration method. Exact correspondences are replaced by iteratively evolving correspondence probabilities which provide the basis for the computation of mean shape and variability model. We validated our approach by computing SSMs using inexact correspondences for kidney and putamen data. In ongoing work, we want to use our methods for automatic classification applications.

Original language	English
Title of host publication	Bildverarbeitung für die Medizin 2007
Number of pages	5
Place of Publication	Berlin, Heidelberg
Publisher	Springer Verlag
Publication date	01.12.2007
Pages	434-438
ISBN (Print)	978-3-540-71090-5
ISBN (Electronic)	978-3-540-71091-2
DOIs	https://doi.org/10.1007/978-3-540-71091-2_87
Publication status	Published - 01.12.2007
Event	Workshop on Bildverarbeitung fur die Medizin 2007 - Munich, Germany Duration: 25.03.2007 → 27.03.2007 Conference number: 97564

UN SDGs

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

Access to Document

10.1007/978-3-540-71091-2_87

Cite this

@inproceedings{b864d122eda24853beeb57de20f4e13d,

title = "Point-Based Statistical Shape Models with Probabilistic Correspondences and Affine EM-ICP",

abstract = "A fundamental problem when computing statistical shape models (SSMs) is the determination of correspondences between the instances. Often, homologies between points that represent the surfaces are assumed which might lead to imprecise mean shape and variation results. We present a novel algorithm based on the affine Expectation Maximization - Iterative Closest Point (EM-ICP) registration method. Exact correspondences are replaced by iteratively evolving correspondence probabilities which provide the basis for the computation of mean shape and variability model. We validated our approach by computing SSMs using inexact correspondences for kidney and putamen data. In ongoing work, we want to use our methods for automatic classification applications.",

author = "Heike Hufnagel and Xavier Pennec and Jan Ehrhardt and Heinz Handels and Nicholas Ayache",

year = "2007",

month = dec,

day = "1",

doi = "10.1007/978-3-540-71091-2_87",

language = "English",

isbn = "978-3-540-71090-5",

series = "Informatik aktuell",

publisher = "Springer Verlag",

pages = "434--438",

booktitle = "Bildverarbeitung f{\"u}r die Medizin 2007",

note = "Workshop on Bildverarbeitung fur die Medizin 2007, BVM 2007 ; Conference date: 25-03-2007 Through 27-03-2007",

}

Hufnagel, H, Pennec, X, Ehrhardt, J , Handels, H & Ayache, N 2007, Point-Based Statistical Shape Models with Probabilistic Correspondences and Affine EM-ICP. in Bildverarbeitung für die Medizin 2007 . Informatik aktuell, Springer Verlag, Berlin, Heidelberg, pp. 434-438, Workshop on Bildverarbeitung fur die Medizin 2007, Munich, Bavaria, Germany, 25.03.07. https://doi.org/10.1007/978-3-540-71091-2_87

Point-Based Statistical Shape Models with Probabilistic Correspondences and Affine EM-ICP. / Hufnagel, Heike; Pennec, Xavier; Ehrhardt, Jan et al.
Bildverarbeitung für die Medizin 2007 . Berlin, Heidelberg: Springer Verlag, 2007. p. 434-438 (Informatik aktuell).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Point-Based Statistical Shape Models with Probabilistic Correspondences and Affine EM-ICP

AU - Hufnagel, Heike

AU - Pennec, Xavier

AU - Ehrhardt, Jan

AU - Handels, Heinz

AU - Ayache, Nicholas

N1 - Conference code: 97564

PY - 2007/12/1

Y1 - 2007/12/1

N2 - A fundamental problem when computing statistical shape models (SSMs) is the determination of correspondences between the instances. Often, homologies between points that represent the surfaces are assumed which might lead to imprecise mean shape and variation results. We present a novel algorithm based on the affine Expectation Maximization - Iterative Closest Point (EM-ICP) registration method. Exact correspondences are replaced by iteratively evolving correspondence probabilities which provide the basis for the computation of mean shape and variability model. We validated our approach by computing SSMs using inexact correspondences for kidney and putamen data. In ongoing work, we want to use our methods for automatic classification applications.

AB - A fundamental problem when computing statistical shape models (SSMs) is the determination of correspondences between the instances. Often, homologies between points that represent the surfaces are assumed which might lead to imprecise mean shape and variation results. We present a novel algorithm based on the affine Expectation Maximization - Iterative Closest Point (EM-ICP) registration method. Exact correspondences are replaced by iteratively evolving correspondence probabilities which provide the basis for the computation of mean shape and variability model. We validated our approach by computing SSMs using inexact correspondences for kidney and putamen data. In ongoing work, we want to use our methods for automatic classification applications.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-84879935251&origin=inward&txGid=41a692b897cb5cee1f0aca66c34d5796

U2 - 10.1007/978-3-540-71091-2_87

DO - 10.1007/978-3-540-71091-2_87

M3 - Conference contribution

SN - 978-3-540-71090-5

T3 - Informatik aktuell

SP - 434

EP - 438

BT - Bildverarbeitung für die Medizin 2007

PB - Springer Verlag

CY - Berlin, Heidelberg

T2 - Workshop on Bildverarbeitung fur die Medizin 2007

Y2 - 25 March 2007 through 27 March 2007

ER -

Point-Based Statistical Shape Models with Probabilistic Correspondences and Affine EM-ICP

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this