A robust and automated cell counting method in quantification of digital breast cancer immunohistochemistry images

Lu Chen; Ji Bao; Qiang Huang; Huaiqiang Sun

doi:10.5114/pjp.2019.90392

eISSN: 2084-9869
ISSN: 1233-9687

Polish Journal of Pathology

Current issue Archive Manuscripts accepted About the journal Supplements Editorial board Abstracting and indexing Subscription Contact Instructions for authors Publication charge Ethical standards and procedures

Editorial System

Submit your Manuscript

Editorial Policies

Sarajevo Declaration on Integrity and Visibility of Scholarly Publications

Open access

3/2019
vol. 70

Send email

Copy url:

abstract:

Original paper

A robust and automated cell counting method in quantification of digital breast cancer immunohistochemistry images

Lu Chen

¹

,

Ji Bao

¹

,

Qiang Huang

²

,

Huaiqiang Sun

²

Department of Pathology, West China Hospital, Sichuan University
Imaging Research Core Facilities, West China Hospital, Sichuan University

Pol J Pathol 2019; 70 (3): 162-173

DOI: https://doi.org/10.5114/pjp.2019.90392

Online publish date: 2019/12/07

View full text Get citation

PlumX metrics:

Quantitative analysis of immunohistochemically stained breast cancer specimens by cell counting is important for prognosis and treatment planning. This paper presents a robust, accurate, and novel method to label immunopositive and immunonegative cells automatically. During preprocessing, we developed an adaptive method to correct the colour aberration caused by imaging conditions. Next, a pixel-level segmentation was performed on preprocessed images using a support vector machine with a radial basis function kernel in HSV colour space. The segmentation result was processed by mathematical morphology operations to correct error-segmented regions and extract the marker for each cell. Validation studies showed that the automated cell-counting method had divergences varying from –5.05% to 3.99% compared with manual counting by a pathologist, indicating considerable agreement of the present automated cell counting method with manual counting. Thus, this method can free pathologists from laborious work and can potentially improve the accuracy and the reproducibility of diagnosis.

keywords:

A robust and automated cell counting method in quantification of digital breast cancer immunohistochemistry images

Lu Chen 1 , Ji Bao 1 , Qiang Huang 2 , Huaiqiang Sun 2

breast cancer, cell counting, immunohistochemistry, support vector machine (SVM), mathematical morphology

Lu Chen

¹

,

Ji Bao

¹

,

Qiang Huang

²

,

Huaiqiang Sun

²