Establishing local correspondences towards compact representations of anatomical structures

Sharon Xiaolei Huang, Nikos Paragios, Dimitris Metaxas

Research output: Contribution to journalConference article

32 Citations (Scopus)

Abstract

Computer-aided diagnosis is often based on comparing a structure of interest with prior models. Such a comparison requires automatic techniques in determining prior models from a set of examples and establishing local correspondences between the structure and the model. In this paper we propose a variational technique for solving the correspondence problem. The proposed method integrates a powerful representation for shapes (implicit functions), a state-of-the-art criterion for global registration (mutual information) and an efficient technique to recover local correspondences (free form deformations) that guarantees one-to-one mapping. Local correspondences can then be used to build compact representations for a structure of interest according to a set of training examples. The registration and statistical modeling of Systolic Left Ventricle shapes in Ultrasonic images demonstrate the potential of the proposed technique.

Original languageEnglish (US)
Pages (from-to)926-934
Number of pages9
JournalLecture Notes in Computer Science
Volume2879
Issue numberPART 2
StatePublished - Dec 1 2003
EventMedical Image Computing and Computer-Assisted Intervention, MICCAI 2003 - 6th International Conference Proceedings - Montreal, Que., Canada
Duration: Nov 15 2003Nov 18 2003

Fingerprint

Correspondence
Registration
Variational techniques
Computer aided diagnosis
Free-form Deformation
Correspondence Problem
Implicit Function
Computer-aided Diagnosis
Left Ventricle
Statistical Modeling
Shape Function
Ultrasonics
Mutual Information
Integrate
Model
Demonstrate

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)

Cite this

@article{dbde0e34edfc4f7caf430821db1e3193,
title = "Establishing local correspondences towards compact representations of anatomical structures",
abstract = "Computer-aided diagnosis is often based on comparing a structure of interest with prior models. Such a comparison requires automatic techniques in determining prior models from a set of examples and establishing local correspondences between the structure and the model. In this paper we propose a variational technique for solving the correspondence problem. The proposed method integrates a powerful representation for shapes (implicit functions), a state-of-the-art criterion for global registration (mutual information) and an efficient technique to recover local correspondences (free form deformations) that guarantees one-to-one mapping. Local correspondences can then be used to build compact representations for a structure of interest according to a set of training examples. The registration and statistical modeling of Systolic Left Ventricle shapes in Ultrasonic images demonstrate the potential of the proposed technique.",
author = "Huang, {Sharon Xiaolei} and Nikos Paragios and Dimitris Metaxas",
year = "2003",
month = "12",
day = "1",
language = "English (US)",
volume = "2879",
pages = "926--934",
journal = "Lecture Notes in Computer Science",
issn = "0302-9743",
publisher = "Springer Verlag",
number = "PART 2",

}

Establishing local correspondences towards compact representations of anatomical structures. / Huang, Sharon Xiaolei; Paragios, Nikos; Metaxas, Dimitris.

In: Lecture Notes in Computer Science, Vol. 2879, No. PART 2, 01.12.2003, p. 926-934.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Establishing local correspondences towards compact representations of anatomical structures

AU - Huang, Sharon Xiaolei

AU - Paragios, Nikos

AU - Metaxas, Dimitris

PY - 2003/12/1

Y1 - 2003/12/1

N2 - Computer-aided diagnosis is often based on comparing a structure of interest with prior models. Such a comparison requires automatic techniques in determining prior models from a set of examples and establishing local correspondences between the structure and the model. In this paper we propose a variational technique for solving the correspondence problem. The proposed method integrates a powerful representation for shapes (implicit functions), a state-of-the-art criterion for global registration (mutual information) and an efficient technique to recover local correspondences (free form deformations) that guarantees one-to-one mapping. Local correspondences can then be used to build compact representations for a structure of interest according to a set of training examples. The registration and statistical modeling of Systolic Left Ventricle shapes in Ultrasonic images demonstrate the potential of the proposed technique.

AB - Computer-aided diagnosis is often based on comparing a structure of interest with prior models. Such a comparison requires automatic techniques in determining prior models from a set of examples and establishing local correspondences between the structure and the model. In this paper we propose a variational technique for solving the correspondence problem. The proposed method integrates a powerful representation for shapes (implicit functions), a state-of-the-art criterion for global registration (mutual information) and an efficient technique to recover local correspondences (free form deformations) that guarantees one-to-one mapping. Local correspondences can then be used to build compact representations for a structure of interest according to a set of training examples. The registration and statistical modeling of Systolic Left Ventricle shapes in Ultrasonic images demonstrate the potential of the proposed technique.

UR - http://www.scopus.com/inward/record.url?scp=0344823904&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0344823904&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0344823904

VL - 2879

SP - 926

EP - 934

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

SN - 0302-9743

IS - PART 2

ER -