A Novel Segmentation Framework.pdf (1.8 MB)
Download file

A novel segmentation framework using sparse random feature in histology images of colon cancer

Download (1.8 MB)
conference contribution
posted on 14.05.2019, 10:51 by K Zhang, H Zhou, L Chen, M Fei, J Wu, P Zhang
In this paper, we present a novel segmentation framework for glandular structures in Hematoxylin and Eosin stained histology images, choosing poorly differentiated colon tissue as an example. The proposed framework’ target is to identify precise epithelial nuclei objects. We start with staining separate to detect all nuclei objects, and deploy multi-resolution morphology operation to map the initial epithelial nuclei positions. We proposed a new bag of words scheme using sparse random feature to classify epithelial nuclei and stroma nuclei objects to adjust the rest nuclei positions. Finally, we can use the boundary of optimized epithelial nuclei objects to segment the glandular structure.

Funding

This work was financially supported by the Natural Science Foundation of Jiangsu Province, China under grant No. BK20170443. Nantong Research Program of Application Foundation under Grant No. GY12016022 and Dr. H Zhou is currently supported by UK EPSRC under Grant EP/N011074/1, and Newton Advanced Fellowship under Grant NA160342.

History

Citation

Communications in Computer and Information Science, 2017, 761, pp. 173-180

Author affiliation

/Organisation/COLLEGE OF SCIENCE AND ENGINEERING/Department of Informatics

Source

Advanced Computational Methods in Life System Modeling and Simulation. ICSEE 2017, LSMS 2017.

Version

AM (Accepted Manuscript)

Published in

Communications in Computer and Information Science

Publisher

Springer Verlag (Germany)

issn

1865-0929

isbn

9789811063695

Copyright date

2017

Available date

14/05/2019

Publisher version

https://link.springer.com/chapter/10.1007/978-981-10-6370-1_17

Language

en