Algorithm and benchmark dataset for stain separation in histology images

Michael T. McCann, Joshita Majumdar, Cheng Peng, Carlos A. Castro, Jelena Kovacevic

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this work, we present a new algorithm and benchmark dataset for stain separation in histology images. Histology is a critical and ubiquitous task in medical practice and research, serving as a gold standard of diagnosis for many diseases. Automating routine histology analysis tasks could reduce health care costs and improve diagnostic accuracy. One challenge in automation is that histology slides vary in their stain intensity and color; we therefore seek a digital method to normalize the appearance of histology images. As histology slides often have multiple stains on them that must be normalized independently, stain separation must occur before normalization. We propose a new digital stain separation method for the universally-used hematoxylin and eosin stain; this method improves on the state-of-the-art by adjusting the contrast of its eosin-only estimate and including a notion of stain interaction. To validate this method, we have collected a new benchmark dataset via chemical destaining containing ground truth images for stain separation, which we release publicly. Our experiments show that our method achieves more accurate stain separation than two comparison methods and that this improvement in separation accuracy leads to improved normalization.

Original languageEnglish (US)
Title of host publication2014 IEEE International Conference on Image Processing, ICIP 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3953-3957
Number of pages5
ISBN (Electronic)9781479957514
DOIs
StatePublished - Jan 28 2014

Fingerprint

Histology
Health care
Automation
Color
Costs
Experiments

Keywords

  • histology
  • stain separation
  • unmixing

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

McCann, M. T., Majumdar, J., Peng, C., Castro, C. A., & Kovacevic, J. (2014). Algorithm and benchmark dataset for stain separation in histology images. In 2014 IEEE International Conference on Image Processing, ICIP 2014 (pp. 3953-3957). [7025803] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIP.2014.7025803

Algorithm and benchmark dataset for stain separation in histology images. / McCann, Michael T.; Majumdar, Joshita; Peng, Cheng; Castro, Carlos A.; Kovacevic, Jelena.

2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 3953-3957 7025803.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

McCann, MT, Majumdar, J, Peng, C, Castro, CA & Kovacevic, J 2014, Algorithm and benchmark dataset for stain separation in histology images. in 2014 IEEE International Conference on Image Processing, ICIP 2014., 7025803, Institute of Electrical and Electronics Engineers Inc., pp. 3953-3957. https://doi.org/10.1109/ICIP.2014.7025803
McCann MT, Majumdar J, Peng C, Castro CA, Kovacevic J. Algorithm and benchmark dataset for stain separation in histology images. In 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 3953-3957. 7025803 https://doi.org/10.1109/ICIP.2014.7025803
McCann, Michael T. ; Majumdar, Joshita ; Peng, Cheng ; Castro, Carlos A. ; Kovacevic, Jelena. / Algorithm and benchmark dataset for stain separation in histology images. 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 3953-3957
@inproceedings{4d35652fd2c24258842ee103f8d57a81,
title = "Algorithm and benchmark dataset for stain separation in histology images",
abstract = "In this work, we present a new algorithm and benchmark dataset for stain separation in histology images. Histology is a critical and ubiquitous task in medical practice and research, serving as a gold standard of diagnosis for many diseases. Automating routine histology analysis tasks could reduce health care costs and improve diagnostic accuracy. One challenge in automation is that histology slides vary in their stain intensity and color; we therefore seek a digital method to normalize the appearance of histology images. As histology slides often have multiple stains on them that must be normalized independently, stain separation must occur before normalization. We propose a new digital stain separation method for the universally-used hematoxylin and eosin stain; this method improves on the state-of-the-art by adjusting the contrast of its eosin-only estimate and including a notion of stain interaction. To validate this method, we have collected a new benchmark dataset via chemical destaining containing ground truth images for stain separation, which we release publicly. Our experiments show that our method achieves more accurate stain separation than two comparison methods and that this improvement in separation accuracy leads to improved normalization.",
keywords = "histology, stain separation, unmixing",
author = "McCann, {Michael T.} and Joshita Majumdar and Cheng Peng and Castro, {Carlos A.} and Jelena Kovacevic",
year = "2014",
month = "1",
day = "28",
doi = "10.1109/ICIP.2014.7025803",
language = "English (US)",
pages = "3953--3957",
booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Algorithm and benchmark dataset for stain separation in histology images

AU - McCann, Michael T.

AU - Majumdar, Joshita

AU - Peng, Cheng

AU - Castro, Carlos A.

AU - Kovacevic, Jelena

PY - 2014/1/28

Y1 - 2014/1/28

N2 - In this work, we present a new algorithm and benchmark dataset for stain separation in histology images. Histology is a critical and ubiquitous task in medical practice and research, serving as a gold standard of diagnosis for many diseases. Automating routine histology analysis tasks could reduce health care costs and improve diagnostic accuracy. One challenge in automation is that histology slides vary in their stain intensity and color; we therefore seek a digital method to normalize the appearance of histology images. As histology slides often have multiple stains on them that must be normalized independently, stain separation must occur before normalization. We propose a new digital stain separation method for the universally-used hematoxylin and eosin stain; this method improves on the state-of-the-art by adjusting the contrast of its eosin-only estimate and including a notion of stain interaction. To validate this method, we have collected a new benchmark dataset via chemical destaining containing ground truth images for stain separation, which we release publicly. Our experiments show that our method achieves more accurate stain separation than two comparison methods and that this improvement in separation accuracy leads to improved normalization.

AB - In this work, we present a new algorithm and benchmark dataset for stain separation in histology images. Histology is a critical and ubiquitous task in medical practice and research, serving as a gold standard of diagnosis for many diseases. Automating routine histology analysis tasks could reduce health care costs and improve diagnostic accuracy. One challenge in automation is that histology slides vary in their stain intensity and color; we therefore seek a digital method to normalize the appearance of histology images. As histology slides often have multiple stains on them that must be normalized independently, stain separation must occur before normalization. We propose a new digital stain separation method for the universally-used hematoxylin and eosin stain; this method improves on the state-of-the-art by adjusting the contrast of its eosin-only estimate and including a notion of stain interaction. To validate this method, we have collected a new benchmark dataset via chemical destaining containing ground truth images for stain separation, which we release publicly. Our experiments show that our method achieves more accurate stain separation than two comparison methods and that this improvement in separation accuracy leads to improved normalization.

KW - histology

KW - stain separation

KW - unmixing

UR - http://www.scopus.com/inward/record.url?scp=84949928035&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949928035&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2014.7025803

DO - 10.1109/ICIP.2014.7025803

M3 - Conference contribution

AN - SCOPUS:84949928035

SP - 3953

EP - 3957

BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -