Novel segmentation algorithm for identification of cell membrane staining in HER2 images

• We presented new approach to membrane staining determination in HER2 images.• Our solution using predefined linear patterns is resistive to noise and artefacts.• The system has shown good performance for HER2 breast cancer images. The paper presents new approach to the problem of a membrane staini...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition letters 2016-12, Vol.84, p.225-231
Main Authors: Wdowiak, Marek, Markiewicz, Tomasz, Osowski, Stanislaw, Patera, Janusz, Kozlowski, Wojciech
Format: Article
Language:English
Subjects:
Algorithms
Breast cancer
Cancer
Complexity
ErbB-2 protein
HER2 images
Image processing
Image segmentation
Masks
Membrane staining
Object recognition
Pattern recognition
Segmentation
Shape recognition
Staining
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:• We presented new approach to membrane staining determination in HER2 images.• Our solution using predefined linear patterns is resistive to noise and artefacts.• The system has shown good performance for HER2 breast cancer images. The paper presents new approach to the problem of a membrane staining determination in HER2 images of breast cancer. It is based on representation of the small membrane sections by the defined linear patterns of different shapes, which combined together allow representing the complex shape of the membrane staining. The discovered linear structures existing in the image are localized and recognized applying the specially devised masks sliding over the whole analyzed image. The method is resistant to the noise inherent in the image and to the varying detail complexity of the image. Its usefulness in HER2 image processing was verified on examples of the HER2 images of the breast cancer representing different grades of membrane staining.
ISSN:0167-8655
1872-7344
DOI:10.1016/j.patrec.2016.10.003