Skip to content. | Skip to navigation

Personal tools
You are here: Home Faculty Bioengineering Full-Time Faculty Dr. Ayman El-Baz MICCAI Tutorial

MICCAI Tutorial

BI_Logo          BioImgLab          BI_Logo

thinline copy.gifthinline copy.gifthinline copy.gif

|  Dr. Ayman El-Baz | People | Projects | Publications | Education | Facilities | Lab Awards | Gallery | Alumni | Thesis| Suppl._Materials |  MICCAI Tutorial |   Books |

 

 

Tutorial - MICCAI 2013 Nagoya, Japan, Sept. 22-26, 2013

Stochastic Modeling for Medical Image Analysis

  

Outline

Stochastic modeling facilitates understanding of natural phenomena depicted in medical anatomical and functional (dynamic) MRI and CT images. Computer-assisted diagnostics calls for fast and accurate unsupervised learning of models from images. The tutorial details efficient stochastic modeling techniques, including (i) shape models of objects-of-interest; (ii) shape and visual appearance models based on analytic learning of 2nd- or higher-order non-parametric Markov-Gibbs random fields, and (iii) appearance models based on precise unsupervised learning of a mixture of pseudo-distributions approximating an empirical marginal probability distribution of pixel/voxel intensities.  The pseudo-distribution, one per object associated with a prominent mode of the empirical distribution, is a linear combination of unimodal distributions, e.g. discrete Gaussians, with a dominant positive and several sign-alternate subordinate components. Integration of the models and learning techniques will be illustrated in application to early detection of lung and prostate cancer, kidney transplant rejection, and autism, as well as to cardiac functionality assessment.

   

Tutorial organizers

Ayman El-Baz,
BioImaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY 40292, USA.

Email: aselba01@exchange.louisville.edu 

Georgy Gimel'farb,

Department of Computer Science, University of Auckland, Auckland 1142, New Zealand.

Email: g.gimelfarb@auckland.ac.nz

  

Tutorial presenters – contributors

Ayman El-Baz,

BioImaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY 40292, USA.

Email: aselba01@exchange.louisville.edu 

 

Georgy Gimel'farb,

Department of Computer Science, University of Auckland, Auckland 1142, New Zealand.

Email: g.gimelfarb@auckland.ac.nz

Ahmed Elnakib,

BioImaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY 40292, USA.
Email: aaelna02@exchange.louisville.edu 

Fahmi Khalifa,

BioImaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY 40292, USA.
Email: fakhal01@exchange.louisville.edu 

Mathew Nitzken,

BioImaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY 40292, USA.
Email: mjnitz02@exchange.louisville.edu

Ahmed Soliman,

BioImaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY 40292, USA.
Email: asnaee01@exchange.louisville.edu 

Amir Alansary,

BioImaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY 40292, USA.
Email: amalan01@exchange.louisville.edu

Mahmoud Mostapha,

BioImaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY 40292, USA.
Email: mmmost01@exchange.louisville.edu

 MICCAI13_tutorial
    
 MICCAI_Program
   

Detailed Program

Stochastic Modeling for Medical Image Analysis    

The objective of this tutorial is to find an accurate mathematical model that describes all possible information in the image. So, the question is: what is the possible information that can be modeled in an image? The answer to this question depends on the applications that these mathematical models will be utilized to analyze. The focus of this tutorial is to find the mathematical model which could improve the performance of the existing registration and segmentation approaches. The most important models that could capture the visual characteristics of an image are (See Fig. 1):

 

a)   Modeling the distribution of the intensity in each object in a particular image,

b    Modeling the interaction between the pixels in each object in the given image, and

c)   Modeling the shape of the objects in the given image.

 Stoc_Models

Fig. 1. Illustration of the proposed joint Markov-Gibbs model of T1-weighted MR brain images

  a)   Modeling the distribution of the intensity in each object in a particular image
In this tutorial we present a new approach for density estimation. The introduced approach is based on modifying Expectation-Maximization (EM) algorithm to approximate an empirical probability density function of scalar data with a Linear Combination of Discrete Gaussians (LCDG). We also propose a novel EM-based sequential technique to get a close initial LCDG approximation the modified EM algorithm should start with. Due to both positive and negative components, the LCDG approximates inter-class transitions more accurately than a conventional mixture of only positive Gaussians.
 Example 1: Density Estimation Using LCDG Probabilistic Model
 Example_001
b) Modeling the interaction between the pixels in each object in the given image
b-1)Neighborhood System for Higher-order Potts MGRF Model  
   MGRF_Neighborhood
     MGRF_Cliques
b-2) 3D Neighborhood System for Potts MGRF Model
MGRF_Neighborhood_3D

b-3) 3D Rotation Invariant MGRF Model

 3DMGRF_figure2
c)   Modeling the shape of the objects in the given image.
   
c-1) Probabilistic Shape Model
 Shape_Priors
 
Applications
 1. Lung Segmenation
Lung_Cross_Sections
Lung_3D
 2. 2D/3D Kidney Segmenation
Kidney_Segmentation_2D_01
 
 Kidney_Segmentation_3D
 3. Segmentation of 3D Magnetic Resonance Angiography
MRA_TOF
 4. Brain Segemnation from T1-MR images
Brain Segmentation    
3D Brain Visualization
 5.  LV Wall Segmentation from 4D Cine MR Images
 Heart_Sections
 
 
 

5. Dynamic Contrast-Enhanced MRI-Based Early Detection of Acute Renal Transplant Rejection

In this tutorial, we present a new framework for early detection of acute renal transplant rejection from dynamic contrast-enhanced MRI. Our framework consists of four steps. First, kidney objects are segmented from adjacent abdominal structures with a geometric (level set-based)  deformable model guided by a stochastic speed function, which accounts for a fourth-order Markov-Gibbs random field (MGRF) model of the kidney/background shape and appearance. Second, local kidney deformations caused by physiological effects are compensated for by a Laplace-based nonrigid registration approach that deforms target kidney objects over a set of closed, equispaced contours (iso-contours) to closely match the reference object. Next, the cortex is segmented as it is the functional kidney unit that is at is primarily affected by the perfusion deficits that underlie the pathophysiology of acute rejection. To characterize rejection, perfusion is estimated from contrast agent kinetics using transient phase empirical indexes,(peak signal intensity, time-to-peak, and initial up-slope), and a steady-phase index defined as the average signal change during the slowly varying tissue distribution phase of agent transit. We used a kn- nearest neighbor classifier to distinguish between rejection and non-rejection. In a cohort of 50 participants, our framework correctly classified 92% of training subjects, 100% of the test subjects as rejection or non-rejection transplant candidates. Thus, our framework holds promise as a reliable diagnostic tool, which is comparable to the biopsy gold standard but without the associated deleterious side effects.

 Kidney_CAD_Framework
 
6. Improving full-cardiac cycle strain estimation from tagged CMR by accurate modeling of 3D image appearance characteristics

This tutorial will focus on the uses of such a a 3-dimensional Markov Gibbs Random Field (MGRF) for use in improving tagged CMR images, along with a detailed explanation and discussion of how to implement the model in programming, and its application to cardiac CMR images. The 3D MGRF model can be used as a selective and highly configurable and controllable method of filtering on a wide variety of data, and can be implemented as an extremely useful filter to achieve many types of results. The usage of such a filter can serve to improve many other applications. Finally, it will be discussed how combining the previously discussed mixture of distributions can be implemented alongside the MGRF to improve its application to cardiac imaging. Discussions involving implementation of the MGRF in a uniform 3-dimensional way, along with weighted and selective MGRF applications will be explored. For all of these discussions general programming guidance and code/pseudo-code will be used to provide a meaningful understanding of the procedures. It is the goal of this tutorial that participants learn not only the uses and benefits of a 3D MGRF for image improvement purposes, but also gain an understanding of how to implement such an approach for their own uses. Specifically, the application of the technique on tagged CMR images will be used to illustrate the effects of the 3D MGRF on real world data.

3DMGRF_figure1
 
 

 

 

 

 

  

 

| Back to Lab Page |

 

Document Actions
Personal tools