Multi-scale colorectal tumour segmentation using a novel coarse to fine strategy

Kun Zhang, Danny Crookes, Jim Diamond, Minrui Fei, Jianguo Wu, Peijian Zhang, Huiyu Zhou

Research output: Contribution to conferencePaper

4 Citations (Scopus)
361 Downloads (Pure)

Abstract

This paper addresses the problem of colorectal tumour segmentation in complex real world imagery. For efficient segmentation, a multi-scale strategy is developed for extracting the potentially cancerous region of interest (ROI) based on colour histograms while searching for the best texture resolution. To achieve better segmentation accuracy, we apply a novel bag-of-visual-words method based on rotation invariant raw statistical features and random projection based l2-norm sparse representation to classify tumour areas in histopathology images. Experimental results on 20 real world digital slides demonstrate that the proposed algorithm results in better recognition accuracy than several state of the art segmentation techniques.
Original languageEnglish
Number of pages12
Publication statusPublished - 19 Sep 2016
Event British Machine Vision Conference 2016 - University of York, York, United Kingdom
Duration: 19 Sep 201619 Sep 2016
http://bmvc2016.cs.york.ac.uk/

Conference

Conference British Machine Vision Conference 2016
Abbreviated titleBMVC 2016
CountryUnited Kingdom
CityYork
Period19/09/201619/09/2016
Internet address

Fingerprint Dive into the research topics of 'Multi-scale colorectal tumour segmentation using a novel coarse to fine strategy'. Together they form a unique fingerprint.

  • Cite this

    Zhang, K., Crookes, D., Diamond, J., Fei, M., Wu, J., Zhang, P., & Zhou, H. (2016). Multi-scale colorectal tumour segmentation using a novel coarse to fine strategy. Paper presented at British Machine Vision Conference 2016, York, United Kingdom.