Automating measurement of renal interstitial fibrosis: Effect of colour spaces on quantification

Wei Keat Tey; Ye Chow Kuang; Joon Joon Khoo; Melanie Po-Leen Ooi; Serge Demidenko

doi:10.1109/I2MTC.2016.7520504

Automating measurement of renal interstitial fibrosis: Effect of colour spaces on quantification

Wei Keat Tey, Ye Chow Kuang, Joon Joon Khoo, Melanie Po-Leen Ooi, Serge Demidenko

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

2 Citations (Scopus)

Abstract

The progression of chronic renal diseases is primarily measured by the extent of interstitial fibrosis and glomerulosclerosis in renal biopsies. The traditional method of interstitial fibrosis quantification uses visual evaluation, which presents high inter- and intra-observer variability. In this paper, we investigate automated quantification methods based on various colour spaces in renal biopsy images. The system identifies and extracts structures in the renal biopsy image based on the colour information presented by the image following a set of knowledge-based rules on the different structures in a microscopic renal biopsy image. The quantification results indicate that a hybrid method which incorporates different colour spaces to segment tissue structures achieves higher accuracy compared to thresholding or clustering methods. It reduces the error of single colour space methods by half, achieving a mean error of 6 percentage points.

Original language	English
Title of host publication	2016 IEEE International Instrumentation and Measurement Technology Conference Proceedings (I²MTC 2016)
Subtitle of host publication	Taipei, Taiwan, 23-26 May 2016
Editors	Alessandra Flammini, Subhas Mukhopadhyay, Shervin Shirmohammadi
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Number of pages	6
ISBN (Electronic)	9781467392204
ISBN (Print)	9781467392211
DOIs	https://doi.org/10.1109/I2MTC.2016.7520504
Publication status	Published - 22 Jul 2016
Event	IEEE International Instrumentation and Measurement Technology Conference 2016 - Taipei, Taiwan Duration: 23 May 2016 → 26 May 2016 Conference number: 33rd http://2016.imtc.ieee-ims.org/ https://ieeexplore.ieee.org/xpl/conhome/7508333/proceeding (Proceedings)

Conference

Conference	IEEE International Instrumentation and Measurement Technology Conference 2016
Abbreviated title	I2MTC 2016
Country/Territory	Taiwan
City	Taipei
Period	23/05/16 → 26/05/16
Internet address	http://2016.imtc.ieee-ims.org/ https://ieeexplore.ieee.org/xpl/conhome/7508333/proceeding (Proceedings)

Keywords

Medical image analysis
Renal fibrosis
Segmentation

Access to Document

10.1109/I2MTC.2016.7520504

Cite this

Tey, W. K., Kuang, Y. C., Khoo, J. J., Ooi, M. P.-L., & Demidenko, S. (2016). Automating measurement of renal interstitial fibrosis: Effect of colour spaces on quantification. In A. Flammini, S. Mukhopadhyay, & S. Shirmohammadi (Eds.), 2016 IEEE International Instrumentation and Measurement Technology Conference Proceedings (I²MTC 2016): Taipei, Taiwan, 23-26 May 2016 Article 7520504 IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/I2MTC.2016.7520504

Tey, Wei Keat ; Kuang, Ye Chow ; Khoo, Joon Joon et al. / Automating measurement of renal interstitial fibrosis : Effect of colour spaces on quantification. 2016 IEEE International Instrumentation and Measurement Technology Conference Proceedings (I²MTC 2016): Taipei, Taiwan, 23-26 May 2016. editor / Alessandra Flammini ; Subhas Mukhopadhyay ; Shervin Shirmohammadi. IEEE, Institute of Electrical and Electronics Engineers, 2016.

@inproceedings{a98b0f60192f430fbab79c2a1019389e,

title = "Automating measurement of renal interstitial fibrosis: Effect of colour spaces on quantification",

abstract = "The progression of chronic renal diseases is primarily measured by the extent of interstitial fibrosis and glomerulosclerosis in renal biopsies. The traditional method of interstitial fibrosis quantification uses visual evaluation, which presents high inter- and intra-observer variability. In this paper, we investigate automated quantification methods based on various colour spaces in renal biopsy images. The system identifies and extracts structures in the renal biopsy image based on the colour information presented by the image following a set of knowledge-based rules on the different structures in a microscopic renal biopsy image. The quantification results indicate that a hybrid method which incorporates different colour spaces to segment tissue structures achieves higher accuracy compared to thresholding or clustering methods. It reduces the error of single colour space methods by half, achieving a mean error of 6 percentage points.",

keywords = "Medical image analysis, Renal fibrosis, Segmentation",

author = "Tey, {Wei Keat} and Kuang, {Ye Chow} and Khoo, {Joon Joon} and Ooi, {Melanie Po-Leen} and Serge Demidenko",

year = "2016",

month = jul,

day = "22",

doi = "10.1109/I2MTC.2016.7520504",

language = "English",

isbn = "9781467392211",

editor = "Alessandra Flammini and Subhas Mukhopadhyay and Shervin Shirmohammadi",

booktitle = "2016 IEEE International Instrumentation and Measurement Technology Conference Proceedings (I2MTC 2016)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "IEEE International Instrumentation and Measurement Technology Conference 2016, I2MTC 2016 ; Conference date: 23-05-2016 Through 26-05-2016",

url = "http://2016.imtc.ieee-ims.org/, https://ieeexplore.ieee.org/xpl/conhome/7508333/proceeding",

}

Tey, WK, Kuang, YC, Khoo, JJ, Ooi, MP-L & Demidenko, S 2016, Automating measurement of renal interstitial fibrosis: Effect of colour spaces on quantification. in A Flammini, S Mukhopadhyay & S Shirmohammadi (eds), 2016 IEEE International Instrumentation and Measurement Technology Conference Proceedings (I²MTC 2016): Taipei, Taiwan, 23-26 May 2016., 7520504, IEEE, Institute of Electrical and Electronics Engineers, IEEE International Instrumentation and Measurement Technology Conference 2016, Taipei, Taiwan, 23/05/16. https://doi.org/10.1109/I2MTC.2016.7520504

Automating measurement of renal interstitial fibrosis: Effect of colour spaces on quantification. / Tey, Wei Keat; Kuang, Ye Chow; Khoo, Joon Joon et al.
2016 IEEE International Instrumentation and Measurement Technology Conference Proceedings (I²MTC 2016): Taipei, Taiwan, 23-26 May 2016. ed. / Alessandra Flammini; Subhas Mukhopadhyay; Shervin Shirmohammadi. IEEE, Institute of Electrical and Electronics Engineers, 2016. 7520504.

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

TY - GEN

T1 - Automating measurement of renal interstitial fibrosis

T2 - IEEE International Instrumentation and Measurement Technology Conference 2016

AU - Tey, Wei Keat

AU - Kuang, Ye Chow

AU - Khoo, Joon Joon

AU - Ooi, Melanie Po-Leen

AU - Demidenko, Serge

N1 - Conference code: 33rd

PY - 2016/7/22

Y1 - 2016/7/22

N2 - The progression of chronic renal diseases is primarily measured by the extent of interstitial fibrosis and glomerulosclerosis in renal biopsies. The traditional method of interstitial fibrosis quantification uses visual evaluation, which presents high inter- and intra-observer variability. In this paper, we investigate automated quantification methods based on various colour spaces in renal biopsy images. The system identifies and extracts structures in the renal biopsy image based on the colour information presented by the image following a set of knowledge-based rules on the different structures in a microscopic renal biopsy image. The quantification results indicate that a hybrid method which incorporates different colour spaces to segment tissue structures achieves higher accuracy compared to thresholding or clustering methods. It reduces the error of single colour space methods by half, achieving a mean error of 6 percentage points.

AB - The progression of chronic renal diseases is primarily measured by the extent of interstitial fibrosis and glomerulosclerosis in renal biopsies. The traditional method of interstitial fibrosis quantification uses visual evaluation, which presents high inter- and intra-observer variability. In this paper, we investigate automated quantification methods based on various colour spaces in renal biopsy images. The system identifies and extracts structures in the renal biopsy image based on the colour information presented by the image following a set of knowledge-based rules on the different structures in a microscopic renal biopsy image. The quantification results indicate that a hybrid method which incorporates different colour spaces to segment tissue structures achieves higher accuracy compared to thresholding or clustering methods. It reduces the error of single colour space methods by half, achieving a mean error of 6 percentage points.

KW - Medical image analysis

KW - Renal fibrosis

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=84980378033&partnerID=8YFLogxK

U2 - 10.1109/I2MTC.2016.7520504

DO - 10.1109/I2MTC.2016.7520504

M3 - Conference Paper

AN - SCOPUS:84980378033

SN - 9781467392211

BT - 2016 IEEE International Instrumentation and Measurement Technology Conference Proceedings (I2MTC 2016)

A2 - Flammini, Alessandra

A2 - Mukhopadhyay, Subhas

A2 - Shirmohammadi, Shervin

PB - IEEE, Institute of Electrical and Electronics Engineers

Y2 - 23 May 2016 through 26 May 2016

ER -

Tey WK, Kuang YC, Khoo JJ, Ooi MPL, Demidenko S. Automating measurement of renal interstitial fibrosis: Effect of colour spaces on quantification. In Flammini A, Mukhopadhyay S, Shirmohammadi S, editors, 2016 IEEE International Instrumentation and Measurement Technology Conference Proceedings (I²MTC 2016): Taipei, Taiwan, 23-26 May 2016. IEEE, Institute of Electrical and Electronics Engineers. 2016. 7520504 doi: 10.1109/I2MTC.2016.7520504

Automating measurement of renal interstitial fibrosis: Effect of colour spaces on quantification

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this