Format

Send to

Choose Destination
Med Image Anal. 2014 Apr;18(3):591-604. doi: 10.1016/j.media.2014.01.010. Epub 2014 Feb 22.

Weakly supervised histopathology cancer image segmentation and classification.

Author information

1
State Key Laboratory of Software Development Environment, Key Laboratory of Biomechanics and Mechanobiology of Ministry of Education, Beihang University, China; Microsoft Research Asia, No. 5 Danling Street, Haidian District, Beijing 10080, PR China. Electronic address: xuyan04@gmail.com.
2
Computer Science Division, University of California, Berkeley, USA. Electronic address: junyanz@eecs.berkeley.edu.
3
Microsoft Research Asia, No. 5 Danling Street, Haidian District, Beijing 10080, PR China. Electronic address: echang@microsoft.com.
4
Department of Pathology, School of Medicine, Zhejiang University, China. Electronic address: lmd@zju.edu.cn.
5
Department of Cognitive Science, University of California, San Diego, CA, USA. Electronic address: ztu@ucsd.edu.

Abstract

Labeling a histopathology image as having cancerous regions or not is a critical task in cancer diagnosis; it is also clinically important to segment the cancer tissues and cluster them into various classes. Existing supervised approaches for image classification and segmentation require detailed manual annotations for the cancer pixels, which are time-consuming to obtain. In this paper, we propose a new learning method, multiple clustered instance learning (MCIL) (along the line of weakly supervised learning) for histopathology image segmentation. The proposed MCIL method simultaneously performs image-level classification (cancer vs. non-cancer image), medical image segmentation (cancer vs. non-cancer tissue), and patch-level clustering (different classes). We embed the clustering concept into the multiple instance learning (MIL) setting and derive a principled solution to performing the above three tasks in an integrated framework. In addition, we introduce contextual constraints as a prior for MCIL, which further reduces the ambiguity in MIL. Experimental results on histopathology colon cancer images and cytology images demonstrate the great advantage of MCIL over the competing methods.

KEYWORDS:

Classification; Clustering; Histopathology image; Image segmentation; Multiple instance learning

PMID:
24637156
DOI:
10.1016/j.media.2014.01.010
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center