Signature maps for automatic identification of prostate cancer from colorimetric analysis of H&E- and IHC-stained histopathological specimens

Ethan Leng, Jonathan C. Henriksen, Anthony E. Rizzardi, Jin Jin, Jung Who Nam, Benjamin M. Brassuer, Andrew D Johnson, Nicholas P. Reder, Joe Koopmeiners, Stephen C. Schmechel, Greg Metzger

Research output: Contribution to journalArticle

Abstract

Prostate cancer (PCa) is a major cause of cancer death among men. The histopathological examination of post-surgical prostate specimens and manual annotation of PCa not only allow for detailed assessment of disease characteristics and extent, but also supply the ground truth for developing of computer-aided diagnosis (CAD) systems for PCa detection before definitive treatment. As manual cancer annotation is tedious and subjective, there have been a number of publications describing methods for automating the procedure via the analysis of digitized whole-slide images (WSIs). However, these studies have focused only on the analysis of WSIs stained with hematoxylin and eosin (H&E), even though there is additional information that could be obtained from immunohistochemical (IHC) staining. In this work, we propose a framework for automating the annotation of PCa that is based on automated colorimetric analysis of both H&E and IHC WSIs stained with a triple-antibody cocktail against high-molecular weight cytokeratin (HMWCK), p63, and α-methylacyl CoA racemase (AMACR). The analysis outputs were then used to train a regression model to estimate the distribution of cancerous epithelium within slides. The approach yielded an AUC of 0.951, sensitivity of 87.1%, and specificity of 90.7% as compared to slide-level annotations, and generalized well to cancers of all grades.

Original languageEnglish (US)
Article number6992
JournalScientific reports
Volume9
Issue number1
DOIs
StatePublished - Dec 1 2019

Fingerprint

Prostatic Neoplasms
Racemases and Epimerases
Neoplasms
Coenzyme A
Hematoxylin
Eosine Yellowish-(YS)
Keratins
Area Under Curve
Publications
Prostate
Cause of Death
Epithelium
Molecular Weight
Staining and Labeling
Sensitivity and Specificity
Antibodies
Therapeutics

PubMed: MeSH publication types

  • Journal Article

Cite this

Signature maps for automatic identification of prostate cancer from colorimetric analysis of H&E- and IHC-stained histopathological specimens. / Leng, Ethan; Henriksen, Jonathan C.; Rizzardi, Anthony E.; Jin, Jin; Nam, Jung Who; Brassuer, Benjamin M.; Johnson, Andrew D; Reder, Nicholas P.; Koopmeiners, Joe; Schmechel, Stephen C.; Metzger, Greg.

In: Scientific reports, Vol. 9, No. 1, 6992, 01.12.2019.

Research output: Contribution to journalArticle

Leng, Ethan ; Henriksen, Jonathan C. ; Rizzardi, Anthony E. ; Jin, Jin ; Nam, Jung Who ; Brassuer, Benjamin M. ; Johnson, Andrew D ; Reder, Nicholas P. ; Koopmeiners, Joe ; Schmechel, Stephen C. ; Metzger, Greg. / Signature maps for automatic identification of prostate cancer from colorimetric analysis of H&E- and IHC-stained histopathological specimens. In: Scientific reports. 2019 ; Vol. 9, No. 1.
@article{d985460f0f424be68a216199bafd5c9f,
title = "Signature maps for automatic identification of prostate cancer from colorimetric analysis of H&E- and IHC-stained histopathological specimens",
abstract = "Prostate cancer (PCa) is a major cause of cancer death among men. The histopathological examination of post-surgical prostate specimens and manual annotation of PCa not only allow for detailed assessment of disease characteristics and extent, but also supply the ground truth for developing of computer-aided diagnosis (CAD) systems for PCa detection before definitive treatment. As manual cancer annotation is tedious and subjective, there have been a number of publications describing methods for automating the procedure via the analysis of digitized whole-slide images (WSIs). However, these studies have focused only on the analysis of WSIs stained with hematoxylin and eosin (H&E), even though there is additional information that could be obtained from immunohistochemical (IHC) staining. In this work, we propose a framework for automating the annotation of PCa that is based on automated colorimetric analysis of both H&E and IHC WSIs stained with a triple-antibody cocktail against high-molecular weight cytokeratin (HMWCK), p63, and α-methylacyl CoA racemase (AMACR). The analysis outputs were then used to train a regression model to estimate the distribution of cancerous epithelium within slides. The approach yielded an AUC of 0.951, sensitivity of 87.1{\%}, and specificity of 90.7{\%} as compared to slide-level annotations, and generalized well to cancers of all grades.",
author = "Ethan Leng and Henriksen, {Jonathan C.} and Rizzardi, {Anthony E.} and Jin Jin and Nam, {Jung Who} and Brassuer, {Benjamin M.} and Johnson, {Andrew D} and Reder, {Nicholas P.} and Joe Koopmeiners and Schmechel, {Stephen C.} and Greg Metzger",
year = "2019",
month = "12",
day = "1",
doi = "10.1038/s41598-019-43486-y",
language = "English (US)",
volume = "9",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Signature maps for automatic identification of prostate cancer from colorimetric analysis of H&E- and IHC-stained histopathological specimens

AU - Leng, Ethan

AU - Henriksen, Jonathan C.

AU - Rizzardi, Anthony E.

AU - Jin, Jin

AU - Nam, Jung Who

AU - Brassuer, Benjamin M.

AU - Johnson, Andrew D

AU - Reder, Nicholas P.

AU - Koopmeiners, Joe

AU - Schmechel, Stephen C.

AU - Metzger, Greg

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Prostate cancer (PCa) is a major cause of cancer death among men. The histopathological examination of post-surgical prostate specimens and manual annotation of PCa not only allow for detailed assessment of disease characteristics and extent, but also supply the ground truth for developing of computer-aided diagnosis (CAD) systems for PCa detection before definitive treatment. As manual cancer annotation is tedious and subjective, there have been a number of publications describing methods for automating the procedure via the analysis of digitized whole-slide images (WSIs). However, these studies have focused only on the analysis of WSIs stained with hematoxylin and eosin (H&E), even though there is additional information that could be obtained from immunohistochemical (IHC) staining. In this work, we propose a framework for automating the annotation of PCa that is based on automated colorimetric analysis of both H&E and IHC WSIs stained with a triple-antibody cocktail against high-molecular weight cytokeratin (HMWCK), p63, and α-methylacyl CoA racemase (AMACR). The analysis outputs were then used to train a regression model to estimate the distribution of cancerous epithelium within slides. The approach yielded an AUC of 0.951, sensitivity of 87.1%, and specificity of 90.7% as compared to slide-level annotations, and generalized well to cancers of all grades.

AB - Prostate cancer (PCa) is a major cause of cancer death among men. The histopathological examination of post-surgical prostate specimens and manual annotation of PCa not only allow for detailed assessment of disease characteristics and extent, but also supply the ground truth for developing of computer-aided diagnosis (CAD) systems for PCa detection before definitive treatment. As manual cancer annotation is tedious and subjective, there have been a number of publications describing methods for automating the procedure via the analysis of digitized whole-slide images (WSIs). However, these studies have focused only on the analysis of WSIs stained with hematoxylin and eosin (H&E), even though there is additional information that could be obtained from immunohistochemical (IHC) staining. In this work, we propose a framework for automating the annotation of PCa that is based on automated colorimetric analysis of both H&E and IHC WSIs stained with a triple-antibody cocktail against high-molecular weight cytokeratin (HMWCK), p63, and α-methylacyl CoA racemase (AMACR). The analysis outputs were then used to train a regression model to estimate the distribution of cancerous epithelium within slides. The approach yielded an AUC of 0.951, sensitivity of 87.1%, and specificity of 90.7% as compared to slide-level annotations, and generalized well to cancers of all grades.

UR - http://www.scopus.com/inward/record.url?scp=85065340365&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065340365&partnerID=8YFLogxK

U2 - 10.1038/s41598-019-43486-y

DO - 10.1038/s41598-019-43486-y

M3 - Article

VL - 9

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 6992

ER -