Robust retinal image registration using expectation maximisation with mutual information

Parminder Singh Reel; Laurence S. Dooley; K. C. P. Wong; Anko Borner

doi:10.1109/ICASSP.2013.6637824

Robust retinal image registration using expectation maximisation with mutual information

Parminder Singh Reel
, Laurence S. Dooley
, K. C. P. Wong
, Anko Borner

Population Health and Genomics

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

22 Citations (Scopus)

Abstract

Retinal images (RI) are widely used to diagnose a variety of eye conditions and diseases such as myopia and diabetic retinopathy. They are inherently characterised by having nonuniform illumination and low-contrast homogeneous regions which represent a unique set of challenges for retinal image registration (RIR). This paper investigates using the expectation maximization for principal component analysis based mutual information (EMPCA-MI) algorithm in RIR. It combines spatial features with mutual information to efficiently achieve improved registration performance. Experimental results for mono-modal RI datasets verify that EMPCA-MI together with Powell-Brent optimization affords superior robustness in comparison with existing RIR methods, including the geometrical features method.

Original language	English
Title of host publication	2013 IEEE International Conference on Acoustics, Speech and Signal Processing
Publisher	IEEE
Pages	1118-1122
Number of pages	5
ISBN (Electronic)	9781479903566
DOIs	https://doi.org/10.1109/ICASSP.2013.6637824
Publication status	Published - 21 Oct 2013
Event	2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Vancouver, Canada Duration: 26 May 2013 → 31 May 2013

Conference

Conference	2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Country/Territory	Canada
City	Vancouver
Period	26/05/13 → 31/05/13

UN SDGs

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

SDG 3 Good Health and Well-being

Access to Document

10.1109/ICASSP.2013.6637824

Cite this

@inproceedings{8c447eaac9e247b58236fa54de07219d,

title = "Robust retinal image registration using expectation maximisation with mutual information",

abstract = "Retinal images (RI) are widely used to diagnose a variety of eye conditions and diseases such as myopia and diabetic retinopathy. They are inherently characterised by having nonuniform illumination and low-contrast homogeneous regions which represent a unique set of challenges for retinal image registration (RIR). This paper investigates using the expectation maximization for principal component analysis based mutual information (EMPCA-MI) algorithm in RIR. It combines spatial features with mutual information to efficiently achieve improved registration performance. Experimental results for mono-modal RI datasets verify that EMPCA-MI together with Powell-Brent optimization affords superior robustness in comparison with existing RIR methods, including the geometrical features method.",

author = "Reel, \{Parminder Singh\} and Dooley, \{Laurence S.\} and Wong, \{K. C. P.\} and Anko Borner",

year = "2013",

month = oct,

day = "21",

doi = "10.1109/ICASSP.2013.6637824",

language = "English",

pages = "1118--1122",

booktitle = "2013 IEEE International Conference on Acoustics, Speech and Signal Processing",

publisher = "IEEE",

note = "2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ; Conference date: 26-05-2013 Through 31-05-2013",

}

Reel, PS, Dooley, LS, Wong, KCP & Borner, A 2013, Robust retinal image registration using expectation maximisation with mutual information. in 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, pp. 1118-1122, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, British Columbia, Canada, 26/05/13. https://doi.org/10.1109/ICASSP.2013.6637824

TY - GEN

T1 - Robust retinal image registration using expectation maximisation with mutual information

AU - Reel, Parminder Singh

AU - Dooley, Laurence S.

AU - Wong, K. C. P.

AU - Borner, Anko

PY - 2013/10/21

Y1 - 2013/10/21

N2 - Retinal images (RI) are widely used to diagnose a variety of eye conditions and diseases such as myopia and diabetic retinopathy. They are inherently characterised by having nonuniform illumination and low-contrast homogeneous regions which represent a unique set of challenges for retinal image registration (RIR). This paper investigates using the expectation maximization for principal component analysis based mutual information (EMPCA-MI) algorithm in RIR. It combines spatial features with mutual information to efficiently achieve improved registration performance. Experimental results for mono-modal RI datasets verify that EMPCA-MI together with Powell-Brent optimization affords superior robustness in comparison with existing RIR methods, including the geometrical features method.

AB - Retinal images (RI) are widely used to diagnose a variety of eye conditions and diseases such as myopia and diabetic retinopathy. They are inherently characterised by having nonuniform illumination and low-contrast homogeneous regions which represent a unique set of challenges for retinal image registration (RIR). This paper investigates using the expectation maximization for principal component analysis based mutual information (EMPCA-MI) algorithm in RIR. It combines spatial features with mutual information to efficiently achieve improved registration performance. Experimental results for mono-modal RI datasets verify that EMPCA-MI together with Powell-Brent optimization affords superior robustness in comparison with existing RIR methods, including the geometrical features method.

U2 - 10.1109/ICASSP.2013.6637824

DO - 10.1109/ICASSP.2013.6637824

M3 - Conference contribution

SP - 1118

EP - 1122

BT - 2013 IEEE International Conference on Acoustics, Speech and Signal Processing

PB - IEEE

T2 - 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Y2 - 26 May 2013 through 31 May 2013

ER -

Robust retinal image registration using expectation maximisation with mutual information

Abstract

Conference

UN SDGs

Access to Document

Fingerprint

Cite this