# Engineering:Project:Bayesian Segmentation

From NAMIC Wiki

Home < Engineering:Project:Bayesian Segmentation

## Contents

# BAYESIAN CLASSIFIER IMAGE FILTER

File:BayesianProgWeekProject.ppt

## Introduction

This ITK filter is a segmentation algorithm which utilizes Bayes's Rule along with an affine-invarient anisotropic smoothing filter.

## Use Case

I'd like to segment a volume or sub-volume into 'N' classes in a very general manner. I will provide the data and the number of classes that I expect and the algorithm will output a labelmap with 'N' classes.

## Data

We are using the Harvard structural datasets.

## Algorithm

- The user sets the number of distinct classes for segmentation: 'N'
- Generate 'N' prior images (default, 'N' uniform prior images)
- Generate 'N' statistical distributions (default, 'N' normal distributions)
- Generate 'N' membership images by applying the statistical distributions to the raw data
- Generate 'N' posterior images by applying Bayes' rule to the prior and membership images
- Smooth the posterior images for 'm' iterations using an affine-invarient anisotropic smoothing filter and renormalize after each iteration (default, m = 5)
- Apply maximum a posteriori rule to apply labeling and finalize segmentation

## The ITK filter design

## Project Status

- Fully incorporated into itkBayesianClassificationImageFilter and itkBayesianClassificationInitializationImageFilter in ITK CVS.
- Fully wrapped in VTK for use in Slicer.
- The working ITK code has been committed to the SandBox.

## Contacts

- John Melonakos @ Georgia Tech
- Luis Ibanez @ Kitware
- Karthik Krishnan @ Kitware