Mitosis counting in breast cancer

Object-level interobserver agreement and comparison to an automatic method

Mitko Veta, Paul J. Van Diest, Mehdi Jiwa, Shaimaa Al-Janabi, Josien P W Pluim

Research output: Contribution to journalArticle

Abstract

Background Tumor proliferation speed, most commonly assessed by counting of mitotic figures in histological slide preparations, is an important biomarker for breast cancer. Although mitosis counting is routinely performed by pathologists, it is a tedious and subjective task with poor reproducibility, particularly among non-experts. Inter- and intraobserver reproducibility of mitosis counting can be improved when a strict protocol is defined and followed. Previous studies have examined only the agreement in terms of the mitotic count or the mitotic activity score. Studies of the observer agreement at the level of individual objects, which can provide more insight into the procedure, have not been performed thus far. Methods The development of automatic mitosis detection methods has received large interest in recent years. Automatic image analysis is viewed as a solution for the problem of subjectivity of mitosis counting by pathologists. In this paper we describe the results from an interobserver agreement study between three human observers and an automatic method, and make two unique contributions. For the first time, we present an analysis of the object-level interobserver agreement on mitosis counting. Furthermore, we train an automatic mitosis detection method that is robust with respect to staining appearance variability and compare it with the performance of expert observers on an "external" dataset, i.e. on histopathology images that originate from pathology labs other than the pathology lab that provided the training data for the automatic method. Results The object-level interobserver study revealed that pathologists often do not agree on individual objects, even if this is not reflected in the mitotic count. The disagreement is larger for objects from smaller size, which suggests that adding a size constraint in the mitosis counting protocol can improve reproducibility. The automatic mitosis detection method can perform mitosis counting in an unbiased way, with substantial agreement with human experts.

Original languageEnglish (US)
Article numbere0161286
JournalPLoS One
Volume11
Issue number8
DOIs
StatePublished - Aug 1 2016
Externally publishedYes

Fingerprint

Pathology
Mitosis
breast neoplasms
mitosis
Breast Neoplasms
Biomarkers
Image analysis
Tumors
reproducibility
methodology
histopathology
biomarkers
image analysis
Staining and Labeling
neoplasms

ASJC Scopus subject areas

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

Cite this

Mitosis counting in breast cancer : Object-level interobserver agreement and comparison to an automatic method. / Veta, Mitko; Van Diest, Paul J.; Jiwa, Mehdi; Al-Janabi, Shaimaa; Pluim, Josien P W.

In: PLoS One, Vol. 11, No. 8, e0161286, 01.08.2016.

Research output: Contribution to journalArticle

Veta, Mitko ; Van Diest, Paul J. ; Jiwa, Mehdi ; Al-Janabi, Shaimaa ; Pluim, Josien P W. / Mitosis counting in breast cancer : Object-level interobserver agreement and comparison to an automatic method. In: PLoS One. 2016 ; Vol. 11, No. 8.
@article{607491700f9f49199771616789f3043b,
title = "Mitosis counting in breast cancer: Object-level interobserver agreement and comparison to an automatic method",
abstract = "Background Tumor proliferation speed, most commonly assessed by counting of mitotic figures in histological slide preparations, is an important biomarker for breast cancer. Although mitosis counting is routinely performed by pathologists, it is a tedious and subjective task with poor reproducibility, particularly among non-experts. Inter- and intraobserver reproducibility of mitosis counting can be improved when a strict protocol is defined and followed. Previous studies have examined only the agreement in terms of the mitotic count or the mitotic activity score. Studies of the observer agreement at the level of individual objects, which can provide more insight into the procedure, have not been performed thus far. Methods The development of automatic mitosis detection methods has received large interest in recent years. Automatic image analysis is viewed as a solution for the problem of subjectivity of mitosis counting by pathologists. In this paper we describe the results from an interobserver agreement study between three human observers and an automatic method, and make two unique contributions. For the first time, we present an analysis of the object-level interobserver agreement on mitosis counting. Furthermore, we train an automatic mitosis detection method that is robust with respect to staining appearance variability and compare it with the performance of expert observers on an {"}external{"} dataset, i.e. on histopathology images that originate from pathology labs other than the pathology lab that provided the training data for the automatic method. Results The object-level interobserver study revealed that pathologists often do not agree on individual objects, even if this is not reflected in the mitotic count. The disagreement is larger for objects from smaller size, which suggests that adding a size constraint in the mitosis counting protocol can improve reproducibility. The automatic mitosis detection method can perform mitosis counting in an unbiased way, with substantial agreement with human experts.",
author = "Mitko Veta and {Van Diest}, {Paul J.} and Mehdi Jiwa and Shaimaa Al-Janabi and Pluim, {Josien P W}",
year = "2016",
month = "8",
day = "1",
doi = "10.1371/journal.pone.0161286",
language = "English (US)",
volume = "11",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "8",

}

TY - JOUR

T1 - Mitosis counting in breast cancer

T2 - Object-level interobserver agreement and comparison to an automatic method

AU - Veta, Mitko

AU - Van Diest, Paul J.

AU - Jiwa, Mehdi

AU - Al-Janabi, Shaimaa

AU - Pluim, Josien P W

PY - 2016/8/1

Y1 - 2016/8/1

N2 - Background Tumor proliferation speed, most commonly assessed by counting of mitotic figures in histological slide preparations, is an important biomarker for breast cancer. Although mitosis counting is routinely performed by pathologists, it is a tedious and subjective task with poor reproducibility, particularly among non-experts. Inter- and intraobserver reproducibility of mitosis counting can be improved when a strict protocol is defined and followed. Previous studies have examined only the agreement in terms of the mitotic count or the mitotic activity score. Studies of the observer agreement at the level of individual objects, which can provide more insight into the procedure, have not been performed thus far. Methods The development of automatic mitosis detection methods has received large interest in recent years. Automatic image analysis is viewed as a solution for the problem of subjectivity of mitosis counting by pathologists. In this paper we describe the results from an interobserver agreement study between three human observers and an automatic method, and make two unique contributions. For the first time, we present an analysis of the object-level interobserver agreement on mitosis counting. Furthermore, we train an automatic mitosis detection method that is robust with respect to staining appearance variability and compare it with the performance of expert observers on an "external" dataset, i.e. on histopathology images that originate from pathology labs other than the pathology lab that provided the training data for the automatic method. Results The object-level interobserver study revealed that pathologists often do not agree on individual objects, even if this is not reflected in the mitotic count. The disagreement is larger for objects from smaller size, which suggests that adding a size constraint in the mitosis counting protocol can improve reproducibility. The automatic mitosis detection method can perform mitosis counting in an unbiased way, with substantial agreement with human experts.

AB - Background Tumor proliferation speed, most commonly assessed by counting of mitotic figures in histological slide preparations, is an important biomarker for breast cancer. Although mitosis counting is routinely performed by pathologists, it is a tedious and subjective task with poor reproducibility, particularly among non-experts. Inter- and intraobserver reproducibility of mitosis counting can be improved when a strict protocol is defined and followed. Previous studies have examined only the agreement in terms of the mitotic count or the mitotic activity score. Studies of the observer agreement at the level of individual objects, which can provide more insight into the procedure, have not been performed thus far. Methods The development of automatic mitosis detection methods has received large interest in recent years. Automatic image analysis is viewed as a solution for the problem of subjectivity of mitosis counting by pathologists. In this paper we describe the results from an interobserver agreement study between three human observers and an automatic method, and make two unique contributions. For the first time, we present an analysis of the object-level interobserver agreement on mitosis counting. Furthermore, we train an automatic mitosis detection method that is robust with respect to staining appearance variability and compare it with the performance of expert observers on an "external" dataset, i.e. on histopathology images that originate from pathology labs other than the pathology lab that provided the training data for the automatic method. Results The object-level interobserver study revealed that pathologists often do not agree on individual objects, even if this is not reflected in the mitotic count. The disagreement is larger for objects from smaller size, which suggests that adding a size constraint in the mitosis counting protocol can improve reproducibility. The automatic mitosis detection method can perform mitosis counting in an unbiased way, with substantial agreement with human experts.

UR - http://www.scopus.com/inward/record.url?scp=84984851022&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84984851022&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0161286

DO - 10.1371/journal.pone.0161286

M3 - Article

VL - 11

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 8

M1 - e0161286

ER -