Computer Aided Semi-Automated Evaluation of HER2 Immunodetection—A Robust Solution for Supporting the Accuracy of Anti HER2 Therapy

Tamás Micsik, Gábor Kiszler, Daniel Szabó, László Krecsák, Csaba Hegedűs, T. Krenács, B. Molnár

Research output: Article

4 Citations (Scopus)

Abstract

HER2-positive breast cancers usually benefit from anti-HER2 therapy, thus, HER2 evaluation became inevitable for patient selection. HER2-negative (IHC 0, 1+) and strong positive (IHC 3+) cases can easily be interpreted with immunohistochemistry, but equivocal (IHC 2+) cases require further analysis of HER2 gene amplification using in situ hybridization. Our study aimed to validate digital pathology and automated image analysis for unbiased evaluation of HER2 immunostains. We developed an image segmentation algorithm for analyzing HER2-immunostaining (4B5 clone) in tissue microarrays of breast cancers. Two pathologists assessed 309 microscopic regions of at least 100 tumor cells each—representing all HER2 positivity groups—according to international guidelines either semi-quantitatively or by using the MembraneQuant software. Scoring results were statistically correlated with each other and with FISH data, and almost perfect agreement was found (inter-method Cohen’s kappa = 0.872, Spearman-rho = 0.928). When clinical relevance (scoring disagreement that may define erroneous treatment selection) was examined high agreement was found (quadratic weighted kappa = 0.967). Image analysis classified cases with excellent correlation with visual evaluation, therefore, MembraneQuant software proved to be a reliable tool for assessing HER2 immunoreactions and supporting better targeting anti-HER2 therapy. As digital analysis of immunomorphological markers allows permanent archiving, standardization and accurate reviewing of results, it supports quality assurance initiatives in diagnostic pathology—especially of equivocal cases which are hard to interpret.

Original languageEnglish
Pages (from-to)1005-1011
Number of pages7
JournalPathology and Oncology Research
Volume21
Issue number4
DOIs
Publication statusPublished - márc. 19 2015

Fingerprint

Software
Breast Neoplasms
erbB-2 Genes
Gene Amplification
Patient Selection
In Situ Hybridization
Therapeutics
Clone Cells
Immunohistochemistry
Guidelines
Pathology
Neoplasms
Pathologists

ASJC Scopus subject areas

  • Cancer Research
  • Oncology
  • Pathology and Forensic Medicine

Cite this

Computer Aided Semi-Automated Evaluation of HER2 Immunodetection—A Robust Solution for Supporting the Accuracy of Anti HER2 Therapy. / Micsik, Tamás; Kiszler, Gábor; Szabó, Daniel; Krecsák, László; Hegedűs, Csaba; Krenács, T.; Molnár, B.

In: Pathology and Oncology Research, Vol. 21, No. 4, 19.03.2015, p. 1005-1011.

Research output: Article

Micsik, Tamás ; Kiszler, Gábor ; Szabó, Daniel ; Krecsák, László ; Hegedűs, Csaba ; Krenács, T. ; Molnár, B. / Computer Aided Semi-Automated Evaluation of HER2 Immunodetection—A Robust Solution for Supporting the Accuracy of Anti HER2 Therapy. In: Pathology and Oncology Research. 2015 ; Vol. 21, No. 4. pp. 1005-1011.
@article{391450dbc61a4df587f709b59206cac5,
title = "Computer Aided Semi-Automated Evaluation of HER2 Immunodetection—A Robust Solution for Supporting the Accuracy of Anti HER2 Therapy",
abstract = "HER2-positive breast cancers usually benefit from anti-HER2 therapy, thus, HER2 evaluation became inevitable for patient selection. HER2-negative (IHC 0, 1+) and strong positive (IHC 3+) cases can easily be interpreted with immunohistochemistry, but equivocal (IHC 2+) cases require further analysis of HER2 gene amplification using in situ hybridization. Our study aimed to validate digital pathology and automated image analysis for unbiased evaluation of HER2 immunostains. We developed an image segmentation algorithm for analyzing HER2-immunostaining (4B5 clone) in tissue microarrays of breast cancers. Two pathologists assessed 309 microscopic regions of at least 100 tumor cells each—representing all HER2 positivity groups—according to international guidelines either semi-quantitatively or by using the MembraneQuant software. Scoring results were statistically correlated with each other and with FISH data, and almost perfect agreement was found (inter-method Cohen’s kappa = 0.872, Spearman-rho = 0.928). When clinical relevance (scoring disagreement that may define erroneous treatment selection) was examined high agreement was found (quadratic weighted kappa = 0.967). Image analysis classified cases with excellent correlation with visual evaluation, therefore, MembraneQuant software proved to be a reliable tool for assessing HER2 immunoreactions and supporting better targeting anti-HER2 therapy. As digital analysis of immunomorphological markers allows permanent archiving, standardization and accurate reviewing of results, it supports quality assurance initiatives in diagnostic pathology—especially of equivocal cases which are hard to interpret.",
keywords = "Breast cancer, Digital pathology, HER2, Image analysis, Immunohistochemistry, Validation",
author = "Tam{\'a}s Micsik and G{\'a}bor Kiszler and Daniel Szab{\'o} and L{\'a}szl{\'o} Krecs{\'a}k and Csaba Hegedűs and T. Kren{\'a}cs and B. Moln{\'a}r",
year = "2015",
month = "3",
day = "19",
doi = "10.1007/s12253-015-9927-6",
language = "English",
volume = "21",
pages = "1005--1011",
journal = "Pathology and Oncology Research",
issn = "1219-4956",
publisher = "Springer Netherlands",
number = "4",

}

TY - JOUR

T1 - Computer Aided Semi-Automated Evaluation of HER2 Immunodetection—A Robust Solution for Supporting the Accuracy of Anti HER2 Therapy

AU - Micsik, Tamás

AU - Kiszler, Gábor

AU - Szabó, Daniel

AU - Krecsák, László

AU - Hegedűs, Csaba

AU - Krenács, T.

AU - Molnár, B.

PY - 2015/3/19

Y1 - 2015/3/19

N2 - HER2-positive breast cancers usually benefit from anti-HER2 therapy, thus, HER2 evaluation became inevitable for patient selection. HER2-negative (IHC 0, 1+) and strong positive (IHC 3+) cases can easily be interpreted with immunohistochemistry, but equivocal (IHC 2+) cases require further analysis of HER2 gene amplification using in situ hybridization. Our study aimed to validate digital pathology and automated image analysis for unbiased evaluation of HER2 immunostains. We developed an image segmentation algorithm for analyzing HER2-immunostaining (4B5 clone) in tissue microarrays of breast cancers. Two pathologists assessed 309 microscopic regions of at least 100 tumor cells each—representing all HER2 positivity groups—according to international guidelines either semi-quantitatively or by using the MembraneQuant software. Scoring results were statistically correlated with each other and with FISH data, and almost perfect agreement was found (inter-method Cohen’s kappa = 0.872, Spearman-rho = 0.928). When clinical relevance (scoring disagreement that may define erroneous treatment selection) was examined high agreement was found (quadratic weighted kappa = 0.967). Image analysis classified cases with excellent correlation with visual evaluation, therefore, MembraneQuant software proved to be a reliable tool for assessing HER2 immunoreactions and supporting better targeting anti-HER2 therapy. As digital analysis of immunomorphological markers allows permanent archiving, standardization and accurate reviewing of results, it supports quality assurance initiatives in diagnostic pathology—especially of equivocal cases which are hard to interpret.

AB - HER2-positive breast cancers usually benefit from anti-HER2 therapy, thus, HER2 evaluation became inevitable for patient selection. HER2-negative (IHC 0, 1+) and strong positive (IHC 3+) cases can easily be interpreted with immunohistochemistry, but equivocal (IHC 2+) cases require further analysis of HER2 gene amplification using in situ hybridization. Our study aimed to validate digital pathology and automated image analysis for unbiased evaluation of HER2 immunostains. We developed an image segmentation algorithm for analyzing HER2-immunostaining (4B5 clone) in tissue microarrays of breast cancers. Two pathologists assessed 309 microscopic regions of at least 100 tumor cells each—representing all HER2 positivity groups—according to international guidelines either semi-quantitatively or by using the MembraneQuant software. Scoring results were statistically correlated with each other and with FISH data, and almost perfect agreement was found (inter-method Cohen’s kappa = 0.872, Spearman-rho = 0.928). When clinical relevance (scoring disagreement that may define erroneous treatment selection) was examined high agreement was found (quadratic weighted kappa = 0.967). Image analysis classified cases with excellent correlation with visual evaluation, therefore, MembraneQuant software proved to be a reliable tool for assessing HER2 immunoreactions and supporting better targeting anti-HER2 therapy. As digital analysis of immunomorphological markers allows permanent archiving, standardization and accurate reviewing of results, it supports quality assurance initiatives in diagnostic pathology—especially of equivocal cases which are hard to interpret.

KW - Breast cancer

KW - Digital pathology

KW - HER2

KW - Image analysis

KW - Immunohistochemistry

KW - Validation

UR - http://www.scopus.com/inward/record.url?scp=84940450419&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84940450419&partnerID=8YFLogxK

U2 - 10.1007/s12253-015-9927-6

DO - 10.1007/s12253-015-9927-6

M3 - Article

C2 - 25788005

AN - SCOPUS:84940450419

VL - 21

SP - 1005

EP - 1011

JO - Pathology and Oncology Research

JF - Pathology and Oncology Research

SN - 1219-4956

IS - 4

ER -