Chapter

World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany

Volume 25/11 of the series IFMBE Proceedings pp 227-230

Bayesian Transductive Markov Random Fields for Interactive Segmentation in Retinal Disorders

  • Noah LeeAffiliated withHeffner Biomedical Imaging Lab (HBIL) Department of Biomedical Engineering, Columbia University
  • , Andrew F. LaineAffiliated withHeffner Biomedical Imaging Lab (HBIL) Department of Biomedical Engineering, Columbia University
  • , R. Theodore SmithAffiliated withDepartment of Ophthalmology, Columbia University

* Final gross prices may vary according to local VAT.

Get Access

Abstract

In the realm of computer aided diagnosis (CAD) interactive segmentation schemes have been well received by physicians, where the combination of human and machine intelligence can provide improved segmentation efficacy with minimal expert intervention [1-3]. Transductive learning (TL) or semi-supervised learning (SSL) is a suitable framework for learning-based interactive segmentation given the scarce label problem. In this paper we present extended work on Bayesian transduction and regularized conditional mixtures for interactive segmentation [3]. We present a Markov random field model integrating a semi-parametric conditional mixture model within a Bayesian transductive learning and inference setting. The model allows efficient learning and inference in a semi-supervised setting given only minimal approximate label information. Preliminary experimental results on multimodal images of retinal disorders such as drusen, geographic atrophy (GA), and choroidal neovascularisation (CNV) with exudates and subretinal fibrosis show promising segmentation performance.

Keywords

Interactive Segmentation Naive Bayes Mixture Models Generative Learning Markov Random Fields Bayesian Transduction