Information theoretic similarity measures in non-rigid registration

William Crum; D L G  Hill; D J  Hawkes

Information theoretic similarity measures in non-rigid registration

William Crum, D L G Hill, D J Hawkes

King's College London

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

33 Citations (Scopus)

Abstract

Mutual Information (MI) and Normalised Mutual Information (NMI) have enjoyed success as image similarity measures in medical image registration. More recently, they have been used for Don-rigid registration, most often evaluated empirically as functions of changing registration parameter. In this paper we present expressions derived from intensity histogram representations of these measures, for their change in response to a local perturbation of a deformation field linking two images. These expressions give some insight into the operation of NMI in registration and are implemented as driving forces within a fluid registration framework. The performance of the measures is tested on publicly available simulated multi-spectral MR brain images.

Original language	English
Title of host publication	INFORMATION PROCESSING IN MEDICAL IMAGING, PROCEEDINGS
Editors	C Taylor, JA Noble
Place of Publication	BERLIN
Publisher	Springer
Pages	378-387
Number of pages	10
ISBN (Print)	3-540-40560-7
Publication status	Published - 2003
Event	18th International Conference on Information Processing in Medical Imaging - AMBLESIDE Duration: 20 Jul 2003 → 25 Jul 2003

Conference

Conference	18th International Conference on Information Processing in Medical Imaging
City	AMBLESIDE
Period	20/07/2003 → 25/07/2003

Cite this

@inbook{74bffb0cfe564a81933de048dffa79e9,

title = "Information theoretic similarity measures in non-rigid registration",

abstract = "Mutual Information (MI) and Normalised Mutual Information (NMI) have enjoyed success as image similarity measures in medical image registration. More recently, they have been used for Don-rigid registration, most often evaluated empirically as functions of changing registration parameter. In this paper we present expressions derived from intensity histogram representations of these measures, for their change in response to a local perturbation of a deformation field linking two images. These expressions give some insight into the operation of NMI in registration and are implemented as driving forces within a fluid registration framework. The performance of the measures is tested on publicly available simulated multi-spectral MR brain images.",

author = "William Crum and Hill, {D L G} and Hawkes, {D J}",

year = "2003",

language = "English",

isbn = "3-540-40560-7",

pages = "378--387",

editor = "C Taylor and JA Noble",

booktitle = "INFORMATION PROCESSING IN MEDICAL IMAGING, PROCEEDINGS",

publisher = "Springer",

note = "18th International Conference on Information Processing in Medical Imaging ; Conference date: 20-07-2003 Through 25-07-2003",

}

TY - CHAP

T1 - Information theoretic similarity measures in non-rigid registration

AU - Crum, William

AU - Hill, D L G

AU - Hawkes, D J

PY - 2003

Y1 - 2003

N2 - Mutual Information (MI) and Normalised Mutual Information (NMI) have enjoyed success as image similarity measures in medical image registration. More recently, they have been used for Don-rigid registration, most often evaluated empirically as functions of changing registration parameter. In this paper we present expressions derived from intensity histogram representations of these measures, for their change in response to a local perturbation of a deformation field linking two images. These expressions give some insight into the operation of NMI in registration and are implemented as driving forces within a fluid registration framework. The performance of the measures is tested on publicly available simulated multi-spectral MR brain images.

AB - Mutual Information (MI) and Normalised Mutual Information (NMI) have enjoyed success as image similarity measures in medical image registration. More recently, they have been used for Don-rigid registration, most often evaluated empirically as functions of changing registration parameter. In this paper we present expressions derived from intensity histogram representations of these measures, for their change in response to a local perturbation of a deformation field linking two images. These expressions give some insight into the operation of NMI in registration and are implemented as driving forces within a fluid registration framework. The performance of the measures is tested on publicly available simulated multi-spectral MR brain images.

M3 - Conference paper

SN - 3-540-40560-7

SP - 378

EP - 387

BT - INFORMATION PROCESSING IN MEDICAL IMAGING, PROCEEDINGS

A2 - Taylor, C

A2 - Noble, JA

PB - Springer

CY - BERLIN

T2 - 18th International Conference on Information Processing in Medical Imaging

Y2 - 20 July 2003 through 25 July 2003

ER -

Information theoretic similarity measures in non-rigid registration

Abstract

Conference

Fingerprint

Cite this