A whole-slide image grading benchmark and tissue classification for cervical cancer precursor lesions with inter-observer variability

Abdulkadir Albayrak; Asli Unlu Akhan; Nurullah Calik; Abdulkerim Capar; Gokhan Bilgin; Behcet Ugur Toreyin; Bahar Muezzinoglu; Ilknur Turkmen; Lutfiye Durak-Ata

doi:10.1007/s11517-021-02388-w

A whole-slide image grading benchmark and tissue classification for cervical cancer precursor lesions with inter-observer variability

Abdulkadir Albayrak, Asli Unlu Akhan, Nurullah Calik, Abdulkerim Capar, Gokhan Bilgin^*, Behcet Ugur Toreyin, Bahar Muezzinoglu, Ilknur Turkmen, Lutfiye Durak-Ata

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

16 Citations (Scopus)

Abstract

The cervical cancer developing from the precancerous lesions caused by the human papillomavirus (HPV) has been one of the preventable cancers with the help of periodic screening. Cervical intraepithelial neoplasia (CIN) and squamous intraepithelial lesion (SIL) are two types of grading conventions widely accepted by pathologists. On the other hand, inter-observer variability is an important issue for final diagnosis. In this paper, a whole-slide image grading benchmark for cervical cancer precursor lesions is created and the “Uterine Cervical Cancer Database” introduced in this article is the first publicly available cervical tissue microscopy image dataset. In addition, a morphological feature representing the angle between the basal membrane (BM) and the major axis of each nucleus in the tissue is proposed. The presence of papillae of the cervical epithelium and overlapping cell problems are also discussed. Besides that, the inter-observer variability is also evaluated by thorough comparisons among decisions of pathologists, as well as the final diagnosis. [Figure not available: see fulltext.].

Original language	English
Pages (from-to)	1545-1561
Number of pages	17
Journal	Medical and Biological Engineering and Computing
Volume	59
Issue number	7-8
DOIs	https://doi.org/10.1007/s11517-021-02388-w
Publication status	Published - Aug 2021

Bibliographical note

Publisher Copyright:
© 2021, International Federation for Medical and Biological Engineering.

Funding

The authors also would like to thank Argenit Company and Istanbul Medipol University Hospital for providing and annotating the whole-slide histopathological images of cervical cancer precursor lesions image dataset. The authors would like to thank the reviewers for all useful and instructive comments on our manuscript. This work is in part funded by ITU BAP MAB-2020-42314 project and also supported by the Scientific Research Projects Coordination Department, Yildiz Technical University, under Project 2014-04-01-KAP01.

Funders	Funder number
Argenit Company
Istanbul Medipol University Hospital
International Technological University	BAP MAB-2020-42314
Yildiz Teknik Üniversitesi	2014-04-01-KAP01

Keywords

Cervical cancer
Cervical intraepithelial neoplasia (CIN)
Digital pathology
Histopathological images
Human papillomavirus
Inter-observer variability
Morphological features
Squamous intraepithelial lesion (SIL)
Whole-slide imaging

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/s11517-021-02388-w

Cite this

Albayrak, A., Akhan, A. U., Calik, N., Capar, A., Bilgin, G., Toreyin, B. U., Muezzinoglu, B., Turkmen, I., & Durak-Ata, L. (2021). A whole-slide image grading benchmark and tissue classification for cervical cancer precursor lesions with inter-observer variability. Medical and Biological Engineering and Computing, 59(7-8), 1545-1561. https://doi.org/10.1007/s11517-021-02388-w

@article{d6110c0a498243e28b0dffc60e04c878,

title = "A whole-slide image grading benchmark and tissue classification for cervical cancer precursor lesions with inter-observer variability",

abstract = "The cervical cancer developing from the precancerous lesions caused by the human papillomavirus (HPV) has been one of the preventable cancers with the help of periodic screening. Cervical intraepithelial neoplasia (CIN) and squamous intraepithelial lesion (SIL) are two types of grading conventions widely accepted by pathologists. On the other hand, inter-observer variability is an important issue for final diagnosis. In this paper, a whole-slide image grading benchmark for cervical cancer precursor lesions is created and the “Uterine Cervical Cancer Database” introduced in this article is the first publicly available cervical tissue microscopy image dataset. In addition, a morphological feature representing the angle between the basal membrane (BM) and the major axis of each nucleus in the tissue is proposed. The presence of papillae of the cervical epithelium and overlapping cell problems are also discussed. Besides that, the inter-observer variability is also evaluated by thorough comparisons among decisions of pathologists, as well as the final diagnosis. [Figure not available: see fulltext.].",

keywords = "Cervical cancer, Cervical intraepithelial neoplasia (CIN), Digital pathology, Histopathological images, Human papillomavirus, Inter-observer variability, Morphological features, Squamous intraepithelial lesion (SIL), Whole-slide imaging",

author = "Abdulkadir Albayrak and Akhan, {Asli Unlu} and Nurullah Calik and Abdulkerim Capar and Gokhan Bilgin and Toreyin, {Behcet Ugur} and Bahar Muezzinoglu and Ilknur Turkmen and Lutfiye Durak-Ata",

note = "Publisher Copyright: {\textcopyright} 2021, International Federation for Medical and Biological Engineering.",

year = "2021",

month = aug,

doi = "10.1007/s11517-021-02388-w",

language = "English",

volume = "59",

pages = "1545--1561",

journal = "Medical and Biological Engineering and Computing",

issn = "0140-0118",

publisher = "Springer Verlag",

number = "7-8",

}

Albayrak, A, Akhan, AU, Calik, N, Capar, A, Bilgin, G, Toreyin, BU, Muezzinoglu, B, Turkmen, I & Durak-Ata, L 2021, 'A whole-slide image grading benchmark and tissue classification for cervical cancer precursor lesions with inter-observer variability', Medical and Biological Engineering and Computing, vol. 59, no. 7-8, pp. 1545-1561. https://doi.org/10.1007/s11517-021-02388-w

TY - JOUR

T1 - A whole-slide image grading benchmark and tissue classification for cervical cancer precursor lesions with inter-observer variability

AU - Albayrak, Abdulkadir

AU - Akhan, Asli Unlu

AU - Calik, Nurullah

AU - Capar, Abdulkerim

AU - Bilgin, Gokhan

AU - Toreyin, Behcet Ugur

AU - Muezzinoglu, Bahar

AU - Turkmen, Ilknur

AU - Durak-Ata, Lutfiye

PY - 2021/8

Y1 - 2021/8

N2 - The cervical cancer developing from the precancerous lesions caused by the human papillomavirus (HPV) has been one of the preventable cancers with the help of periodic screening. Cervical intraepithelial neoplasia (CIN) and squamous intraepithelial lesion (SIL) are two types of grading conventions widely accepted by pathologists. On the other hand, inter-observer variability is an important issue for final diagnosis. In this paper, a whole-slide image grading benchmark for cervical cancer precursor lesions is created and the “Uterine Cervical Cancer Database” introduced in this article is the first publicly available cervical tissue microscopy image dataset. In addition, a morphological feature representing the angle between the basal membrane (BM) and the major axis of each nucleus in the tissue is proposed. The presence of papillae of the cervical epithelium and overlapping cell problems are also discussed. Besides that, the inter-observer variability is also evaluated by thorough comparisons among decisions of pathologists, as well as the final diagnosis. [Figure not available: see fulltext.].

AB - The cervical cancer developing from the precancerous lesions caused by the human papillomavirus (HPV) has been one of the preventable cancers with the help of periodic screening. Cervical intraepithelial neoplasia (CIN) and squamous intraepithelial lesion (SIL) are two types of grading conventions widely accepted by pathologists. On the other hand, inter-observer variability is an important issue for final diagnosis. In this paper, a whole-slide image grading benchmark for cervical cancer precursor lesions is created and the “Uterine Cervical Cancer Database” introduced in this article is the first publicly available cervical tissue microscopy image dataset. In addition, a morphological feature representing the angle between the basal membrane (BM) and the major axis of each nucleus in the tissue is proposed. The presence of papillae of the cervical epithelium and overlapping cell problems are also discussed. Besides that, the inter-observer variability is also evaluated by thorough comparisons among decisions of pathologists, as well as the final diagnosis. [Figure not available: see fulltext.].

KW - Cervical cancer

KW - Cervical intraepithelial neoplasia (CIN)

KW - Digital pathology

KW - Histopathological images

KW - Human papillomavirus

KW - Inter-observer variability

KW - Morphological features

KW - Squamous intraepithelial lesion (SIL)

KW - Whole-slide imaging

UR - http://www.scopus.com/inward/record.url?scp=85110277156&partnerID=8YFLogxK

U2 - 10.1007/s11517-021-02388-w

DO - 10.1007/s11517-021-02388-w

M3 - Article

C2 - 34245400

AN - SCOPUS:85110277156

SN - 0140-0118

VL - 59

SP - 1545

EP - 1561

JO - Medical and Biological Engineering and Computing

JF - Medical and Biological Engineering and Computing

IS - 7-8

ER -

A whole-slide image grading benchmark and tissue classification for cervical cancer precursor lesions with inter-observer variability

Abstract

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this