Special Section on Digital Pathology

Connecting Markov random fields and active contour models: application to gland segmentation and classification

[+] Author Affiliations
Jun Xu

Nanjing University of Information Science and Technology, Jiangsu Key Laboratory of Big Data Analysis Technique, Nanjing, China

James P. Monaco

Inspirata, Tampa, Florida, United States

Rachel Sparks

University College of London, Center for Medical Image Computing, London, United Kingdom

Anant Madabhushi

Case Western Reserve University, Department of Biomedical Engineering, Cleveland, Ohio, United States

J. Med. Imag. 4(2), 021107 (Mar 28, 2017). doi:10.1117/1.JMI.4.2.021107
History: Received August 2, 2016; Accepted February 20, 2017
Text Size: A A A

Abstract.  We introduce a Markov random field (MRF)-driven region-based active contour model (MaRACel) for histological image segmentation. This Bayesian segmentation method combines a region-based active contour (RAC) with an MRF. State-of-the-art RAC models assume that every spatial location in the image is statistically independent, thereby ignoring valuable contextual information among spatial locations. To address this shortcoming, we incorporate an MRF prior into energy term of the RAC. This requires a formulation of the Markov prior consistent with the continuous variational framework characteristic of active contours; consequently, we introduce a continuous analog to the discrete Potts model. Based on the automated segmentation boundary of glands by MaRACel model, explicit shape descriptors are then employed to distinguish prostate glands belonging to Gleason patterns 3 (G3) and 4 (G4). To demonstrate the effectiveness of MaRACel, we compare its performance to the popular models proposed by Chan and Vese (CV) and Rousson and Deriche (RD) with respect to the following tasks: (1) the segmentation of prostatic acini (glands) and (2) the differentiation of G3 and G4 glands. On almost 600 prostate biopsy needle images, MaRACel was shown to have higher average dice coefficients, overlap ratios, sensitivities, specificities, and positive predictive values both in terms of segmentation accuracy and ability to discriminate between G3 and G4 glands compared to the CV and RD models.

Figures in this Article
© 2017 Society of Photo-Optical Instrumentation Engineers

Citation

Jun Xu ; James P. Monaco ; Rachel Sparks and Anant Madabhushi
"Connecting Markov random fields and active contour models: application to gland segmentation and classification", J. Med. Imag. 4(2), 021107 (Mar 28, 2017). ; http://dx.doi.org/10.1117/1.JMI.4.2.021107


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

PubMed Articles
Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.