Analysis of retinal vascular biomarkers for early detection of diabetes

J. Zhang; B. Dashtbozorg; F. Huang; T.T.J.M. Berendschot; B.M. ter Haar Romeny

doi:10.1007/978-3-319-68195-5_88

Analysis of retinal vascular biomarkers for early detection of diabetes

J. Zhang
, B. Dashtbozorg
, F. Huang
, T.T.J.M. Berendschot
, B.M. ter Haar Romeny

Medical Image Analysis

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

8 Citations (Scopus)

1 Downloads (Pure)

Abstract

This paper presents an automated retinal vessel analysis system for the measurement and statistical analysis of vascular biomarkers. The proposed retinal vessel enhancement, segmentation, optic disc and fovea detection algorithms provide fundamental tools for extracting the vascular network within the predefined region of interest (ROI). Based on that, the artery/vein classification, vessel caliber, curvature and fractal dimension measurement tools are used to assess the quantitative vascular biomarkers: width, tortuosity, and fractal dimension. A statistical analysis on the extracted geometric biomarkers is set up using a dataset provided by the Maastricht study with the aim of exploring the associations between different vessel biomarkers and type 2 diabetes mellitus. A linear regression analysis is used to model the relationships between different factors. The results indicate that the vascular biomarker variables have associations with diabetes. These findings demonstrate the possibility of applying the proposed pipeline tools on further analysis of vessel biomarkers for the computer-aided diagnosis.

Original language	English
Title of host publication	ViPIMAGE 2017
Subtitle of host publication	Proceedings of the VI ECCOMAS Thematic Conference on Computational Vision and Medical Image Processing Porto, Portugal, October 18-20, 2017
Editors	J.M.R.S. Tavares, R.M. Natal Jorge
Place of Publication	Cham
Publisher	Springer
Pages	811-817
Number of pages	7
ISBN (Electronic)	978-3-319-68195-5
ISBN (Print)	978-3-319-68194-8
DOIs	https://doi.org/10.1007/978-3-319-68195-5_88
Publication status	Published - 1 Jan 2018
Event	European Congress on Computational Methods in Applied Sciences and Engineering, ECCOMAS 2017 - Porto, Portugal Duration: 18 Oct 2017 → 20 Oct 2017 https://paginas.fe.up.pt/~vipimage/

Publication series

Name	Lecture Notes in Computational Vision and Biomechanics
Publisher	Springer
Volume	27

Conference

Conference	European Congress on Computational Methods in Applied Sciences and Engineering, ECCOMAS 2017
Abbreviated title	ECCOMAS 2017
Country/Territory	Portugal
City	Porto
Period	18/10/17 → 20/10/17
Internet address	https://paginas.fe.up.pt/~vipimage/

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Computer-aided diagnosis
Diabetes mellitus
Retinal image analysis
Vessel biomarkers

Access to Document

10.1007/978-3-319-68195-5_88

Cite this

Zhang, J., Dashtbozorg, B., Huang, F., Berendschot, T. T. J. M., & ter Haar Romeny, B. M. (2018). Analysis of retinal vascular biomarkers for early detection of diabetes. In J. M. R. S. Tavares, & R. M. Natal Jorge (Eds.), ViPIMAGE 2017: Proceedings of the VI ECCOMAS Thematic Conference on Computational Vision and Medical Image Processing Porto, Portugal, October 18-20, 2017 (pp. 811-817). (Lecture Notes in Computational Vision and Biomechanics; Vol. 27). Springer. https://doi.org/10.1007/978-3-319-68195-5_88

Zhang, J. ; Dashtbozorg, B. ; Huang, F. et al. / Analysis of retinal vascular biomarkers for early detection of diabetes. ViPIMAGE 2017: Proceedings of the VI ECCOMAS Thematic Conference on Computational Vision and Medical Image Processing Porto, Portugal, October 18-20, 2017. editor / J.M.R.S. Tavares ; R.M. Natal Jorge. Cham : Springer, 2018. pp. 811-817 (Lecture Notes in Computational Vision and Biomechanics).

@inproceedings{fedba5dde3af43e8b12f012b18469872,

title = "Analysis of retinal vascular biomarkers for early detection of diabetes",

abstract = "This paper presents an automated retinal vessel analysis system for the measurement and statistical analysis of vascular biomarkers. The proposed retinal vessel enhancement, segmentation, optic disc and fovea detection algorithms provide fundamental tools for extracting the vascular network within the predefined region of interest (ROI). Based on that, the artery/vein classification, vessel caliber, curvature and fractal dimension measurement tools are used to assess the quantitative vascular biomarkers: width, tortuosity, and fractal dimension. A statistical analysis on the extracted geometric biomarkers is set up using a dataset provided by the Maastricht study with the aim of exploring the associations between different vessel biomarkers and type 2 diabetes mellitus. A linear regression analysis is used to model the relationships between different factors. The results indicate that the vascular biomarker variables have associations with diabetes. These findings demonstrate the possibility of applying the proposed pipeline tools on further analysis of vessel biomarkers for the computer-aided diagnosis.",

keywords = "Computer-aided diagnosis, Diabetes mellitus, Retinal image analysis, Vessel biomarkers",

author = "J. Zhang and B. Dashtbozorg and F. Huang and T.T.J.M. Berendschot and \{ter Haar Romeny\}, B.M.",

year = "2018",

month = jan,

day = "1",

doi = "10.1007/978-3-319-68195-5\_88",

language = "English",

isbn = "978-3-319-68194-8",

series = "Lecture Notes in Computational Vision and Biomechanics",

publisher = "Springer",

pages = "811--817",

editor = "J.M.R.S. Tavares and \{Natal Jorge\}, R.M.",

booktitle = "ViPIMAGE 2017",

address = "Germany",

note = "European Congress on Computational Methods in Applied Sciences and Engineering, ECCOMAS 2017, ECCOMAS 2017 ; Conference date: 18-10-2017 Through 20-10-2017",

url = "https://paginas.fe.up.pt/\textasciitilde{}vipimage/",

}

Zhang, J, Dashtbozorg, B, Huang, F, Berendschot, TTJM & ter Haar Romeny, BM 2018, Analysis of retinal vascular biomarkers for early detection of diabetes. in JMRS Tavares & RM Natal Jorge (eds), ViPIMAGE 2017: Proceedings of the VI ECCOMAS Thematic Conference on Computational Vision and Medical Image Processing Porto, Portugal, October 18-20, 2017. Lecture Notes in Computational Vision and Biomechanics, vol. 27, Springer, Cham, pp. 811-817, European Congress on Computational Methods in Applied Sciences and Engineering, ECCOMAS 2017, Porto, Portugal, 18/10/17. https://doi.org/10.1007/978-3-319-68195-5_88

Analysis of retinal vascular biomarkers for early detection of diabetes. / Zhang, J.; Dashtbozorg, B.; Huang, F. et al.
ViPIMAGE 2017: Proceedings of the VI ECCOMAS Thematic Conference on Computational Vision and Medical Image Processing Porto, Portugal, October 18-20, 2017. ed. / J.M.R.S. Tavares; R.M. Natal Jorge. Cham: Springer, 2018. p. 811-817 (Lecture Notes in Computational Vision and Biomechanics; Vol. 27).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Analysis of retinal vascular biomarkers for early detection of diabetes

AU - Zhang, J.

AU - Dashtbozorg, B.

AU - Huang, F.

AU - Berendschot, T.T.J.M.

AU - ter Haar Romeny, B.M.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - This paper presents an automated retinal vessel analysis system for the measurement and statistical analysis of vascular biomarkers. The proposed retinal vessel enhancement, segmentation, optic disc and fovea detection algorithms provide fundamental tools for extracting the vascular network within the predefined region of interest (ROI). Based on that, the artery/vein classification, vessel caliber, curvature and fractal dimension measurement tools are used to assess the quantitative vascular biomarkers: width, tortuosity, and fractal dimension. A statistical analysis on the extracted geometric biomarkers is set up using a dataset provided by the Maastricht study with the aim of exploring the associations between different vessel biomarkers and type 2 diabetes mellitus. A linear regression analysis is used to model the relationships between different factors. The results indicate that the vascular biomarker variables have associations with diabetes. These findings demonstrate the possibility of applying the proposed pipeline tools on further analysis of vessel biomarkers for the computer-aided diagnosis.

AB - This paper presents an automated retinal vessel analysis system for the measurement and statistical analysis of vascular biomarkers. The proposed retinal vessel enhancement, segmentation, optic disc and fovea detection algorithms provide fundamental tools for extracting the vascular network within the predefined region of interest (ROI). Based on that, the artery/vein classification, vessel caliber, curvature and fractal dimension measurement tools are used to assess the quantitative vascular biomarkers: width, tortuosity, and fractal dimension. A statistical analysis on the extracted geometric biomarkers is set up using a dataset provided by the Maastricht study with the aim of exploring the associations between different vessel biomarkers and type 2 diabetes mellitus. A linear regression analysis is used to model the relationships between different factors. The results indicate that the vascular biomarker variables have associations with diabetes. These findings demonstrate the possibility of applying the proposed pipeline tools on further analysis of vessel biomarkers for the computer-aided diagnosis.

KW - Computer-aided diagnosis

KW - Diabetes mellitus

KW - Retinal image analysis

KW - Vessel biomarkers

UR - https://www.scopus.com/pages/publications/85032392139

U2 - 10.1007/978-3-319-68195-5_88

DO - 10.1007/978-3-319-68195-5_88

M3 - Conference contribution

AN - SCOPUS:85032392139

SN - 978-3-319-68194-8

T3 - Lecture Notes in Computational Vision and Biomechanics

SP - 811

EP - 817

BT - ViPIMAGE 2017

A2 - Tavares, J.M.R.S.

A2 - Natal Jorge, R.M.

PB - Springer

CY - Cham

T2 - European Congress on Computational Methods in Applied Sciences and Engineering, ECCOMAS 2017

Y2 - 18 October 2017 through 20 October 2017

ER -

Zhang J, Dashtbozorg B, Huang F, Berendschot TTJM , ter Haar Romeny BM. Analysis of retinal vascular biomarkers for early detection of diabetes. In Tavares JMRS, Natal Jorge RM, editors, ViPIMAGE 2017: Proceedings of the VI ECCOMAS Thematic Conference on Computational Vision and Medical Image Processing Porto, Portugal, October 18-20, 2017. Cham: Springer. 2018. p. 811-817. (Lecture Notes in Computational Vision and Biomechanics). doi: 10.1007/978-3-319-68195-5_88

Analysis of retinal vascular biomarkers for early detection of diabetes

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this