Multichannel Spectral Image Enhancement for Visualizing Diabetic Retinopathy Lesions

Pauli Fält; Masahiro Yamaguchi; Yuri Murakami; Lauri Laaksonen; Lasse Lensu; Ela Claridge; Markku Hauta-kasari; Hannu Uusitalo

doi:10.1007/978-3-319-07998-1_7

Multichannel Spectral Image Enhancement for Visualizing Diabetic Retinopathy Lesions

Pauli Fält, Masahiro Yamaguchi, Yuri Murakami, Lauri Laaksonen, Lasse Lensu, Ela Claridge, Markku Hauta-kasari, Hannu Uusitalo

Computer Science

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

1 Citation (Scopus)

185 Downloads (Pure)

Abstract

Spectral imaging is a useful tool in many fields of scientific research and industry. Spectral images contain both spatial and spectral information of the scene. Spectral information can be used for effective visualization of the features-of-interest. One approach is to use spectral image enhancement techniques to improve the diagnostic accuracy of medical image technologies like retinal imaging. In this paper, two multichannel spectral image enhancement methods and a technique to further improve the visualization are presented. The methods are tested on four multispectral retinal images which contain diabetic retinopathy lesions. Both of the methods improved the detectability and quantitative contrast of the diabetic lesions when compared to standard color images and are potentially valuable for clinicians and automated image analyses.

Original language	English
Title of host publication	Image and Signal Processing
Subtitle of host publication	6th International Conference, ICISP 2014, Cherbourg, France, June 30 – July 2, 2014. Proceedings
Editors	Abderrahim Elmoataz, Olivier Lezoray, Fathallah Nouboud, Driss Mammass
Publisher	Springer
Pages	52-60
Volume	8509
ISBN (Electronic)	9783319079981
ISBN (Print)	9783319079974
DOIs	https://doi.org/10.1007/978-3-319-07998-1_7
Publication status	Published - 2014
Event	6th International Conference, ICISP 2014 - Cherbourg, France, France Duration: 30 Jun 2014 → 2 Jul 2014

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	8509
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	6th International Conference, ICISP 2014
Country/Territory	France
City	Cherbourg, France,
Period	30/06/14 → 2/07/14

Keywords

spectral image
multispectral imaging
principal component analysis
enhancement
retina
diabetes mellitus
diabetic retinopathy

UN SDGs

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

Access to Document

10.1007/978-3-319-07998-1_7Licence: None: All rights reserved

Falt_et_al_multichannel_spectral_image_2014Accepted author manuscript, 1.24 MBLicence: None: All rights reserved

Modular discrete-wavelength light source synchronised with an intensity imaging camera for high-speed multispectral
Claridge, E. (Principal Investigator) & Styles, I. (Co-Investigator)
Engineering & Physical Science Research Council
1/10/07 → 31/01/09
Project: Research Councils

Cite this

Fält, P., Yamaguchi, M., Murakami, Y., Laaksonen, L., Lensu, L., Claridge, E., Hauta-kasari, M., & Uusitalo, H. (2014). Multichannel Spectral Image Enhancement for Visualizing Diabetic Retinopathy Lesions. In A. Elmoataz, O. Lezoray, F. Nouboud, & D. Mammass (Eds.), Image and Signal Processing: 6th International Conference, ICISP 2014, Cherbourg, France, June 30 – July 2, 2014. Proceedings (Vol. 8509, pp. 52-60). (Lecture Notes in Computer Science; Vol. 8509). Springer. https://doi.org/10.1007/978-3-319-07998-1_7

Fält, Pauli ; Yamaguchi, Masahiro ; Murakami, Yuri et al. / Multichannel Spectral Image Enhancement for Visualizing Diabetic Retinopathy Lesions. Image and Signal Processing: 6th International Conference, ICISP 2014, Cherbourg, France, June 30 – July 2, 2014. Proceedings. editor / Abderrahim Elmoataz ; Olivier Lezoray ; Fathallah Nouboud ; Driss Mammass. Vol. 8509 Springer, 2014. pp. 52-60 (Lecture Notes in Computer Science).

@inbook{0cfd8eddcb1a4d86b9a36bb89c1830ad,

title = "Multichannel Spectral Image Enhancement for Visualizing Diabetic Retinopathy Lesions",

abstract = "Spectral imaging is a useful tool in many fields of scientific research and industry. Spectral images contain both spatial and spectral information of the scene. Spectral information can be used for effective visualization of the features-of-interest. One approach is to use spectral image enhancement techniques to improve the diagnostic accuracy of medical image technologies like retinal imaging. In this paper, two multichannel spectral image enhancement methods and a technique to further improve the visualization are presented. The methods are tested on four multispectral retinal images which contain diabetic retinopathy lesions. Both of the methods improved the detectability and quantitative contrast of the diabetic lesions when compared to standard color images and are potentially valuable for clinicians and automated image analyses.",

keywords = "spectral image, multispectral imaging, principal component analysis, enhancement, retina, diabetes mellitus, diabetic retinopathy",

author = "Pauli F{\"a}lt and Masahiro Yamaguchi and Yuri Murakami and Lauri Laaksonen and Lasse Lensu and Ela Claridge and Markku Hauta-kasari and Hannu Uusitalo",

year = "2014",

doi = "10.1007/978-3-319-07998-1_7",

language = "English",

isbn = "9783319079974",

volume = "8509",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "52--60",

editor = "Abderrahim Elmoataz and Olivier Lezoray and Fathallah Nouboud and Driss Mammass",

booktitle = "Image and Signal Processing",

note = "6th International Conference, ICISP 2014 ; Conference date: 30-06-2014 Through 02-07-2014",

}

Fält, P, Yamaguchi, M, Murakami, Y, Laaksonen, L, Lensu, L, Claridge, E, Hauta-kasari, M & Uusitalo, H 2014, Multichannel Spectral Image Enhancement for Visualizing Diabetic Retinopathy Lesions. in A Elmoataz, O Lezoray, F Nouboud & D Mammass (eds), Image and Signal Processing: 6th International Conference, ICISP 2014, Cherbourg, France, June 30 – July 2, 2014. Proceedings. vol. 8509, Lecture Notes in Computer Science, vol. 8509, Springer, pp. 52-60, 6th International Conference, ICISP 2014, Cherbourg, France, France, 30/06/14. https://doi.org/10.1007/978-3-319-07998-1_7

Multichannel Spectral Image Enhancement for Visualizing Diabetic Retinopathy Lesions. / Fält, Pauli; Yamaguchi, Masahiro; Murakami, Yuri et al.
Image and Signal Processing: 6th International Conference, ICISP 2014, Cherbourg, France, June 30 – July 2, 2014. Proceedings. ed. / Abderrahim Elmoataz; Olivier Lezoray; Fathallah Nouboud; Driss Mammass. Vol. 8509 Springer, 2014. p. 52-60 (Lecture Notes in Computer Science; Vol. 8509).

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

TY - CHAP

T1 - Multichannel Spectral Image Enhancement for Visualizing Diabetic Retinopathy Lesions

AU - Fält, Pauli

AU - Yamaguchi, Masahiro

AU - Murakami, Yuri

AU - Laaksonen, Lauri

AU - Lensu, Lasse

AU - Claridge, Ela

AU - Hauta-kasari, Markku

AU - Uusitalo, Hannu

PY - 2014

Y1 - 2014

N2 - Spectral imaging is a useful tool in many fields of scientific research and industry. Spectral images contain both spatial and spectral information of the scene. Spectral information can be used for effective visualization of the features-of-interest. One approach is to use spectral image enhancement techniques to improve the diagnostic accuracy of medical image technologies like retinal imaging. In this paper, two multichannel spectral image enhancement methods and a technique to further improve the visualization are presented. The methods are tested on four multispectral retinal images which contain diabetic retinopathy lesions. Both of the methods improved the detectability and quantitative contrast of the diabetic lesions when compared to standard color images and are potentially valuable for clinicians and automated image analyses.

AB - Spectral imaging is a useful tool in many fields of scientific research and industry. Spectral images contain both spatial and spectral information of the scene. Spectral information can be used for effective visualization of the features-of-interest. One approach is to use spectral image enhancement techniques to improve the diagnostic accuracy of medical image technologies like retinal imaging. In this paper, two multichannel spectral image enhancement methods and a technique to further improve the visualization are presented. The methods are tested on four multispectral retinal images which contain diabetic retinopathy lesions. Both of the methods improved the detectability and quantitative contrast of the diabetic lesions when compared to standard color images and are potentially valuable for clinicians and automated image analyses.

KW - spectral image

KW - multispectral imaging

KW - principal component analysis

KW - enhancement

KW - retina

KW - diabetes mellitus

KW - diabetic retinopathy

U2 - 10.1007/978-3-319-07998-1_7

DO - 10.1007/978-3-319-07998-1_7

M3 - Other chapter contribution

SN - 9783319079974

VL - 8509

T3 - Lecture Notes in Computer Science

SP - 52

EP - 60

BT - Image and Signal Processing

A2 - Elmoataz, Abderrahim

A2 - Lezoray, Olivier

A2 - Nouboud, Fathallah

A2 - Mammass, Driss

PB - Springer

T2 - 6th International Conference, ICISP 2014

Y2 - 30 June 2014 through 2 July 2014

ER -

Fält P, Yamaguchi M, Murakami Y, Laaksonen L, Lensu L, Claridge E et al. Multichannel Spectral Image Enhancement for Visualizing Diabetic Retinopathy Lesions. In Elmoataz A, Lezoray O, Nouboud F, Mammass D, editors, Image and Signal Processing: 6th International Conference, ICISP 2014, Cherbourg, France, June 30 – July 2, 2014. Proceedings. Vol. 8509. Springer. 2014. p. 52-60. (Lecture Notes in Computer Science). doi: 10.1007/978-3-319-07998-1_7

Multichannel Spectral Image Enhancement for Visualizing Diabetic Retinopathy Lesions

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Fingerprint

Projects

Modular discrete-wavelength light source synchronised with an intensity imaging camera for high-speed multispectral

Cite this