Image segmentation using disjunctive normal Bayesian shape and appearance models

Mesadi, Fitsum and Erdil, Ertunç and Çetin, Müjdat and Taşdizen, Tolga (2018) Image segmentation using disjunctive normal Bayesian shape and appearance models. IEEE Transactions on Medical Imaging, 37 (1). pp. 293-305. ISSN 0278-0062 (Print) 1558-254X (Online)

This is the latest version of this item.

[thumbnail of mesadi_TMI17_FINAL_VERSION.pdf] PDF
mesadi_TMI17_FINAL_VERSION.pdf
Restricted to Registered users only

Download (722kB) | Request a copy

Abstract

The use of appearance and shape priors in image segmentation is known to improve accuracy; however, existing techniques have several drawbacks. For instance, most active shape and appearance models require landmark points and assume unimodal shape and appearance distributions, and the level set representation does not support construction of local priors. In this paper, we present novel appearance and shape models for image segmentation based on a differentiable implicit parametric shape representation called a disjunctive normal shape model (DNSM). The DNSM is formed by the disjunction of polytopes, which themselves are formed by the conjunctions of half-spaces. The DNSM's parametric nature allows the use of powerful local prior statistics, and its implicit nature removes the need to use landmarks and easily handles topological changes. In a Bayesian inference framework, we model arbitrary shape and appearance distributions using nonparametric density estimations, at any local scale. The proposed local shape prior results in accurate segmentation even when very few training shapes are available, because the method generates a rich set of shape variations by locally combining training samples. We demonstrate the performance of the framework by applying it to both 2-D and 3-D data sets with emphasis on biomedical image segmentation applications.
Item Type: Article
Uncontrolled Keywords: Segmentation; disjunctive normal forms; shape priors; appearance models; Bayesian; variational methods
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Faculty of Engineering and Natural Sciences > Academic programs > Electronics
Faculty of Engineering and Natural Sciences
Depositing User: Müjdat Çetin
Date Deposited: 05 Aug 2019 22:02
Last Modified: 17 May 2023 12:08
URI: https://research.sabanciuniv.edu/id/eprint/38693

Available Versions of this Item

Actions (login required)

View Item
View Item