IBIA

Statistical modeling

in medical imaging

 

  People

  Software


  MSMI main

      IBIA





Research Group

"Methods of Statistical Modeling in Medical Imaging"

The research group - founded in September 2008 within the Institute for

Biomedical Image Analysis (IBIA) - is dealing with the development of statistical

models of human anatomy and physiological processes. In this context the

focus of the research group is twofold:

 

The first focus is the development, extension and application of algorihms

and methods that allow the automatic creation of statistical models of shape

and appearance in 2, 3 and 4 (time series) dimensions. This incorporates the

following fields of (medical) image anaylsis:

 

    • Segmentation using statistical prior knowledge
    • Rigid and non-rigid registration
    • Statistical methods for dimensionality reduction
    • Statistical methods for classification and (nonlinear) regression

 

The second focus is the application of the developed statistical models of shape

and appearance for diagnostic, therapeutic and interventional procedures.

This covers especially the following topics:

 

  • Assessment of pathogenetic factors using 2, 3 or 4 (3D + time) dimensional

    images (e.g. x-ray,ultrasound, CT, MR, PET, SPECT)

  • Investigation of correspondences between specific diseases and specific

    properties (e.g. shape, inner structure, appearance) of an organ or organ part

  • Prediction of relevant parameters for diagnostis or therapy planning using

    medical image data of patients

  • Visualization of pathogenetic variations of shape and appearance among

    a population

 

The basis for this research is formed by the so called "InShape" models that have

already been developed at the IBIA and were already successfully used for

the segmentation of medical images(more>>)

 

Moreover, InShape models were used for the automatic and objective

placement of regions of interest (ROIs) and the assessment/prediction of

pathogenetic factors and biomechanical paramters (more>>)

 

All developed algorithms and applications are implemented using C++. The

open-source toolkits ITK and VTK form the basis for these implementations.

By this means different image-processing and image-analysis modules have been

developed at the IBIA.

In the following a brief overview of these modules will be given:

 

 

  • Image preprocessing module

 

This module provides an interface to selected (partly ITK) filters for image blurring,

smoothing, thresholding, morphological operations, transformations,

resampling,... in combination with 3 image viewers the are

showing an image block in 3 orthogonal directions.

 

Screenshot of the image preprocessing module of the I-PRESP image processing and

analysis framework.

 

 

  • Level set segmentation module

 

This module provides access to the ITK Level set toolbox. In particulary to the

fast marching level seets, active geodesic level sets and threshold level set filter.

In combination with basic manual 2D segmentation tools it provides functionalilty

for interactive semi-automatic segmentation of 3D image data.

 

Demo video of a segementation of the left cardiac ventricle using fast marching

and active geodesic level sets (flash player needed)

 

Für den Inhalt dieser Seite ist eine neuere Version von Adobe Flash Player erforderlich.

Adobe Flash Player herunterladen

 

 

  • InShape model creation module

 

This module allows the automatic creation of 3D shape and appearance (InShape)

models based on deformation fields created.

In order to establish correspondences different combinations of rigid, affine and

elastic registration (diffeomorphic demons, B-Spline registration) can be used.

As input the user must provide image data and segmented binary labes of the

organ that shall be modeled.

 

Screenshot of the InShape model creation dialogue

 

Para

 

 

Screenshot of the dialogue for regression model calculation and parameter prediciton

 

 

 

  • Model based segmentation module

 

With this module the created models can directly be used for segmentation.

A combination of model based segmentation and level set segmentation is

used for the automatic segmentation of 3D (+time) medical image data.

 

Proximal femur segmentation in CT image using 3D InShape model+level sets (left)

and 3D segmentation result (right) (flash player needed)

 

Für den Inhalt dieser Seite ist eine neuere Version von Adobe Flash Player erforderlich.

Adobe Flash Player herunterladen

Für den Inhalt dieser Seite ist eine neuere Version von Adobe Flash Player erforderlich.

Adobe Flash Player herunterladen

 

3D endocardium segmentation using InShape model + level sets (flash player needed)

 

Für den Inhalt dieser Seite ist eine neuere Version von Adobe Flash Player erforderlich.

Adobe Flash Player herunterladen

 

 

  • InShape model explorer module

 

Using this module the shape and appearance variations represented

by different PCA modes can be visualized using different types of representations.

Moreover, user-defined model instances can be created and saved for further processing.

 

Demo video shwoing the model explorer module (flash player needed)

 

Für den Inhalt dieser Seite ist eine neuere Version von Adobe Flash Player erforderlich.

Adobe Flash Player herunterladen

 

 

  • Visualization module

 

This module provides tools for 3D surface rendering

of binary data using marching cubes algorithm. The modeled scene can be

edited by changing colors, lightning, type of surface representation, texturing,...

 

Screenshot of the 3D visualization module

 

 

 

2D/3D registration module XSePT

(X-ray "Segistration" Process Toolkit)

 

XSePT is a generic scientific tool for model-based 2D/3D image "segistration".

It provides functionality for the (semi) automatic registration of either static 3D images

(e.g. CT, MRI) or 3D InShape models on 2D images (e.g. x-ray).

For this purpose digitally reconstructed radiographs (DRR) are computed using

techniques like ray casting and wobbled splatting.

XSePT was developed at the IBIA by DI Philipp Steininger

 

Screenshot of the 2D/3D "segistration" module

 

 

Demo video of 2D/3D hip registration using XSePT(flash player needed):

 

Für den Inhalt dieser Seite ist eine neuere Version von Adobe Flash Player erforderlich.

Adobe Flash Player herunterladen

 
 

 

Contact:
Karl D. Fritscher, MD, PhD
Head of the Research Group
Room: G3 41
Tel: +43-50-8648-3866
Fax: +43-50-8648-673866
karl.fritscher@umit.at