Image Segmentation Using Disjunctive Normal Bayesian Shape and Appearance Models

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 repr...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on medical imaging 2018-01, Vol.37 (1), p.293-305
Main Authors: Mesadi, Fitsum, Erdil, Ertunc, Cetin, Mujdat, Tasdizen, Tolga
Format: Article
Language:English
Subjects:
Algorithms
appearance models
Bayes methods
Bayes Theorem
Bayesian
Bayesian analysis
Biomedical imaging
Brain - diagnostic imaging
Disjunction
disjunctive normal forms
Half spaces
Humans
Image processing
Image Processing, Computer-Assisted - methods
Image segmentation
Level set
Magnetic Resonance Imaging
Male
Markov analysis
Mathematical models
Medical imaging
Models, Theoretical
Polytopes
Principal component analysis
Prostate - diagnostic imaging
Representations
Segmentation
Shape
shape priors
Spine - diagnostic imaging
Statistical analysis
Statistical inference
Statistical methods
Training
variational methods
Walking - physiology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0278-0062
1558-254X
DOI:10.1109/TMI.2017.2756929