University of Leicester
Browse

sorry, we can't preview this file

6180457.pdf (18.47 MB)

Multiple morphological constraints based complex gland segmentation in colorectal cancer pathology image analysis

Download (18.47 MB)
Version 2 2021-01-19, 08:54
Version 1 2020-06-26, 09:43
journal contribution
posted on 2021-01-19, 08:54 authored by K Zhang, J Fu, L Hua, P Zhang, Y Shao, Sheng Xu, Huiyu Zhou, Li Chen, Jing Wang
Histological assessment of glands is one of the major concerns in colon cancer grading. Considering that poorly differentiated colorectal glands cannot be accurately segmented, we propose an approach for segmentation of glands in colon cancer images, based on the characteristics of lumens and rough gland boundaries. First, we use a U-net for stain separation to obtain H-, E-, and background stain intensity maps. Subsequently, epithelial nucleus is identified on the histopathology images, and the lumen segmentation is performed on the background intensity map. Then, we use the axis of least inertia based similar triangles as the spatial characteristics of lumens and epithelial nucleus, and a triangle membership is used to select glandular contour candidates from epithelial nucleus. By connecting lumens and epithelial nucleus, more accurate gland segmentation is performed based on the rough gland boundary. The proposed stain separation approach is unsupervised, and the stain separation makes the category information contained in the H&E image easy to identify and deal with the uneven stain intensity and the inconspicuous stain difference. In this project, we use deep learning to achieve stain separation by predicting the stain coefficient. Under the deep learning framework, we design a stain coefficient interval model to improve the stain generalization performance. Another innovation is that we propose the combination of the internal lumen contour of adenoma and the outer contour of epithelial cells to obtain a precise gland contour. We compare the performance of the proposed algorithm against that of several state of the art technologies on publicly available datasets. The results show that the segmentation approach combining the characteristics of lumens and rough gland boundary have better segmentation accuracy.

History

Author affiliation

Department of Informatics

Version

  • VoR (Version of Record)

Published in

Complexity

Volume

2020

Publisher

Hindawi

issn

1076-2787

Acceptance date

2020-06-23

Copyright date

2020

Available date

2020-07-28

Language

en

Usage metrics

    University of Leicester Publications

    Categories

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC