Robust hierarchical density estimation and regression for re-stained histological whole slide image co-registration

Jun Jiang, Nicholas Larson, Naresh Prodduturi, Thomas J Flotte, Steven Hart

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

For many disease conditions, tissue samples are colored with multiple dyes and stains to add contrast and location information for specific proteins to accurately identify and diagnose disease. This presents a computational challenge for digital pathology, as whole-slide images (WSIs) need to be properly overlaid (i.e. registered) to identify co-localized features. Traditional image registration methods sometimes fail due to the high variation of cell density and insufficient texture information in WSIs–particularly at high magnifications. In this paper, we proposed a robust image registration strategy to align re-stained WSIs precisely and efficiently. This method is applied to 30 pairs of immunohistochemical (IHC) stains and their hematoxylin and eosin (H&E) counterparts. Our approach advances the existing methods in three key ways. First, we introduce refinements to existing image registration methods. Second, we present an effective weighting strategy using kernel density estimation to mitigate registration errors. Third, we account for the linear relationship across WSI levels to improve accuracy. Our experiments show significant decreases in registration errors when matching IHC and H&E pairs, enabling subcellular-level analysis on stained and re-stained histological images. We also provide a tool to allow users to develop their own registration benchmarking experiments.

Original languageEnglish (US)
Article numbere0220074
JournalPloS one
Volume14
Issue number7
DOIs
StatePublished - Jan 1 2019

Fingerprint

Image registration
Coloring Agents
dyes
Pathology
Benchmarking
Hematoxylin
Eosine Yellowish-(YS)
Spatial Analysis
disease diagnosis
Textures
Experiments
methodology
Tissue
Cell Count
texture
Proteins
seeds
proteins
cells
sampling

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Robust hierarchical density estimation and regression for re-stained histological whole slide image co-registration. / Jiang, Jun; Larson, Nicholas; Prodduturi, Naresh; Flotte, Thomas J; Hart, Steven.

In: PloS one, Vol. 14, No. 7, e0220074, 01.01.2019.

Research output: Contribution to journalArticle

@article{b68d7b7093704866b0bb47517f4ca175,
title = "Robust hierarchical density estimation and regression for re-stained histological whole slide image co-registration",
abstract = "For many disease conditions, tissue samples are colored with multiple dyes and stains to add contrast and location information for specific proteins to accurately identify and diagnose disease. This presents a computational challenge for digital pathology, as whole-slide images (WSIs) need to be properly overlaid (i.e. registered) to identify co-localized features. Traditional image registration methods sometimes fail due to the high variation of cell density and insufficient texture information in WSIs–particularly at high magnifications. In this paper, we proposed a robust image registration strategy to align re-stained WSIs precisely and efficiently. This method is applied to 30 pairs of immunohistochemical (IHC) stains and their hematoxylin and eosin (H&E) counterparts. Our approach advances the existing methods in three key ways. First, we introduce refinements to existing image registration methods. Second, we present an effective weighting strategy using kernel density estimation to mitigate registration errors. Third, we account for the linear relationship across WSI levels to improve accuracy. Our experiments show significant decreases in registration errors when matching IHC and H&E pairs, enabling subcellular-level analysis on stained and re-stained histological images. We also provide a tool to allow users to develop their own registration benchmarking experiments.",
author = "Jun Jiang and Nicholas Larson and Naresh Prodduturi and Flotte, {Thomas J} and Steven Hart",
year = "2019",
month = "1",
day = "1",
doi = "10.1371/journal.pone.0220074",
language = "English (US)",
volume = "14",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "7",

}

TY - JOUR

T1 - Robust hierarchical density estimation and regression for re-stained histological whole slide image co-registration

AU - Jiang, Jun

AU - Larson, Nicholas

AU - Prodduturi, Naresh

AU - Flotte, Thomas J

AU - Hart, Steven

PY - 2019/1/1

Y1 - 2019/1/1

N2 - For many disease conditions, tissue samples are colored with multiple dyes and stains to add contrast and location information for specific proteins to accurately identify and diagnose disease. This presents a computational challenge for digital pathology, as whole-slide images (WSIs) need to be properly overlaid (i.e. registered) to identify co-localized features. Traditional image registration methods sometimes fail due to the high variation of cell density and insufficient texture information in WSIs–particularly at high magnifications. In this paper, we proposed a robust image registration strategy to align re-stained WSIs precisely and efficiently. This method is applied to 30 pairs of immunohistochemical (IHC) stains and their hematoxylin and eosin (H&E) counterparts. Our approach advances the existing methods in three key ways. First, we introduce refinements to existing image registration methods. Second, we present an effective weighting strategy using kernel density estimation to mitigate registration errors. Third, we account for the linear relationship across WSI levels to improve accuracy. Our experiments show significant decreases in registration errors when matching IHC and H&E pairs, enabling subcellular-level analysis on stained and re-stained histological images. We also provide a tool to allow users to develop their own registration benchmarking experiments.

AB - For many disease conditions, tissue samples are colored with multiple dyes and stains to add contrast and location information for specific proteins to accurately identify and diagnose disease. This presents a computational challenge for digital pathology, as whole-slide images (WSIs) need to be properly overlaid (i.e. registered) to identify co-localized features. Traditional image registration methods sometimes fail due to the high variation of cell density and insufficient texture information in WSIs–particularly at high magnifications. In this paper, we proposed a robust image registration strategy to align re-stained WSIs precisely and efficiently. This method is applied to 30 pairs of immunohistochemical (IHC) stains and their hematoxylin and eosin (H&E) counterparts. Our approach advances the existing methods in three key ways. First, we introduce refinements to existing image registration methods. Second, we present an effective weighting strategy using kernel density estimation to mitigate registration errors. Third, we account for the linear relationship across WSI levels to improve accuracy. Our experiments show significant decreases in registration errors when matching IHC and H&E pairs, enabling subcellular-level analysis on stained and re-stained histological images. We also provide a tool to allow users to develop their own registration benchmarking experiments.

UR - http://www.scopus.com/inward/record.url?scp=85070082370&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070082370&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0220074

DO - 10.1371/journal.pone.0220074

M3 - Article

C2 - 31339943

AN - SCOPUS:85070082370

VL - 14

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 7

M1 - e0220074

ER -