segmentation in the field medicine

64
Segmentation In The Field Medicine Advanced Image Processing course By: Ibrahim Jubran Presented To: Prof. Hagit Hel- Or

Upload: elia

Post on 07-Jan-2016

29 views

Category:

Documents


4 download

DESCRIPTION

Segmentation In The Field Medicine. Advanced Image Processing course By: Ibrahim Jubran Presented To: Prof. Hagit Hel-Or. What we will go through today. A little inspiration. Medical image segmentation methods: -Deformable Models. -Markov Random Fields. Results. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Segmentation In The Field Medicine

Segmentation In The Field Medicine

Advanced Image Processing course

By: Ibrahim Jubran

Presented To: Prof. Hagit Hel-Or

Page 2: Segmentation In The Field Medicine

What we will go through today

• A little inspiration.

• Medical image segmentation methods:

- Deformable Models.

- Markov Random Fields.

• Results.

Page 3: Segmentation In The Field Medicine

Why Let A Human Do It, When The Computer Does It

Better?• “Image data is of immense practical

importance in medical informatics.”

• For instance: CAT, MRI, CT, X-Ray, Ultrasound.All represented as images, and as images, they can be processed to extract meaningful information such as: volume, shape, motion of organs, layers, or to detect any abnormalities.

Page 4: Segmentation In The Field Medicine

Why Let A Human Do It, When The Computer Does It

Better? Cont.

• Here’s a task for you:

Look at this image:could you manually mark the boundaries of the two abnormal regions?

Answer: Maybe…

Page 5: Segmentation In The Field Medicine

Not Bad...

Page 6: Segmentation In The Field Medicine

And… What if I told you to do it in 3D?

Answer?You would probably fail badly.

Page 7: Segmentation In The Field Medicine

But… the computer, on other hand, dealt with it perfectly:

Page 8: Segmentation In The Field Medicine

Common Methods:Deformable Models

• Deformable models are curves whose deformations are determined by the displacement of a discrete number of control points along the curve.

• Advantage: usually very fast convergence, depending on the predetermined number of control points.

• Disadvantage: Topology dependent: a model can capture only one ROI, therefore in images with multiple ROIs we need to initialize multiple models.

Page 9: Segmentation In The Field Medicine

Deformable models

• A widely used method in the medicine field is the Deformable Models, which is divided into two main categories:- The Parametric Deformable Models.- The Geometric Deformable Models.

•We shall discuss each of them briefly.

Page 10: Segmentation In The Field Medicine

Geometric Models

• Geometric Models use a distance transformation to define the shape from the n-dimentional to an n+1-dimentional domain (where n=1 for curves, n=2 for surfaces on the image plane…)

Page 11: Segmentation In The Field Medicine

Example of a transformation

• Here you see a transformation from 1D to 2D.

Page 12: Segmentation In The Field Medicine

Geometric Models cont.

• Advantages: 1) The evolving interface can be described by a single function even if it consists of more than one curve. 2) The shape can be defined in a domain with dimensionality similar to the dataset space (for example, for 2D segmentation, a curve is transformed into a 2D surface) -> more mathematically straightforward integration of shape and appearance.

Page 13: Segmentation In The Field Medicine

In Other Words…

• We transform the n dimensional image into an n+1 dimensional image, then we try to find the best position for a “plane” , called the “zero level set”, to be in.

• We start from the highest point and descend, until the change in the gradient is below a predefined threshold.

Page 14: Segmentation In The Field Medicine

• The distance function:• g is the speed function, C is our zero

level set

• C’ forces the boundaries to be smooth.

And Formally…

Page 15: Segmentation In The Field Medicine

Geometric Deformable Models Example

Page 16: Segmentation In The Field Medicine

Geometric Models Results

Page 17: Segmentation In The Field Medicine

Geometric Deformable Models Short demonstration

Click to watch a demonstration of the MRF

Page 18: Segmentation In The Field Medicine

Parametric Models

• Also known as “Active contours”, or Snakes.Sounds familiar?

• The following slides are taken from Saar Arbel’s presentation about Snakes.

Five instances of the evolution of a region based deformable model

Page 19: Segmentation In The Field Medicine

What is a snake?A framework for drawing an object outline from a possibly noisy 2D image.An energy-minimizing curve guided by external constraint forces and influenced by image forces that pull it towards features (lines, edges).Represents an object boundary or some other salient image feature as a parametric curve

Page 20: Segmentation In The Field Medicine

Every snake includes:External Energy FunctionInternal Energy FunctionA set of k points (in the discreet world)or a continuous  function that will represent the points

Page 21: Segmentation In The Field Medicine
Page 22: Segmentation In The Field Medicine

Snakes are autonomous and self-adapting in their search for a minimal energy state

So... Why snakes?

They can be easily manipulated using external image forces

They can be used to track dynamic objects in temporal as well as the spatial dimensions

Page 23: Segmentation In The Field Medicine

Common Methods:Learned Based Classification

• Learning based pixel and region classification is among the popular approaches for image segmentation.

• Those methods use the advantages of supervised learning (training from examples) to assign a probability for each image site of belonging to the region of interest (ROI).

Page 24: Segmentation In The Field Medicine

The MRF & The Cartoon Model

A cartoon model

Page 25: Segmentation In The Field Medicine

The Markov Random Field

• The name “Markov Random Field” might sound like a hard and scary subject at first… I thought so too when I started reading about it…

• Unfortunately I still do.

Page 26: Segmentation In The Field Medicine

An unrelated photo of Homer Simpson

• Click to watch a demonstration of the MRF

• https://www.youtube.com/watch?v=hfOfAqLWo5c

Page 27: Segmentation In The Field Medicine

The MRF & The Cartoon Model

• The MRF uses a model called the “cartoon model”, which assumes that the “world” consists of regions where low level features change slowly, but across the boundaries these features change abruptly.

• Our goal is: to find , a “cartoon”, which is a simplified version of the input image but with Labels attached to the regions.

Page 28: Segmentation In The Field Medicine

& The Cartoon Model

is modeled as a discrete random variable taking values in .

Page 29: Segmentation In The Field Medicine

The Cartoon Model Cont.

• The discontinuities between those regions form a curve (the contour).

• (, ) form a segmentation.

•We will only focus on finding the best , because once is determined, can be easily obtained.

Page 30: Segmentation In The Field Medicine

More Cartoon Model Examples

Original labelled (𝜔 , 𝛤 )

Page 31: Segmentation In The Field Medicine

The Probabilistic ApproachFor Finding The Model

• For each possible segmentation / cartoon of the input image G we want to give a probability measure that describes how suitable the cartoon is, for this specific image.

• Let be the set of all possible segmentations, Note that is finite!

Page 32: Segmentation In The Field Medicine

The Probabilistic Approach cont.

• Assumptions: in this approach we assume that we have 2 sets of variables:1) The observation random variables Y.

ℱ Y ,the observation , represents the low- level features in the image.2) The hidden random variables X.

The hidden entity X represents the segmentation itself.

Page 33: Segmentation In The Field Medicine

Observation and Hidden Variables

Low level features,for example:

Page 34: Segmentation In The Field Medicine

Defining the Parameters needed

• First we need to define how well a segmentation fits the image features ℱ.P(| ℱ) – the image model.

•We want every image to posses a set of properties. P() – the prior, tells us how well satisfies these properties.

Page 35: Segmentation In The Field Medicine

Illustration Of P(| ℱ)

original P(| ℱ) is high P(| ℱ) is low

Page 36: Segmentation In The Field Medicine

Example

•We want the regions to be more homogeneous.

For example,In this image P()would be a large number

Page 37: Segmentation In The Field Medicine

Example cont.

But, In this image P() would be a very small number

Page 38: Segmentation In The Field Medicine

Our Goal

• Our goal is to maximize P(|ℱ), since the higher this probability is, the more suitable the segmentation fits the image features ℱ.

Page 39: Segmentation In The Field Medicine

An unrelated photo of Homer Simpson (again)

• Click to watch a demonstration of the MRF

Page 40: Segmentation In The Field Medicine

A Lesson In Probability

• As you might remember (probably not) from Probability lectures,

• Since is constant for each image and so is dropped, therefor, we are looking for that maximizes the posterior.

Page 41: Segmentation In The Field Medicine

Defining the Parameters needed Cont.

• In addition to the probability distributions that we defined, our model also depend on certain parameters that we denote by .

• In the supervised segmentation we assume these parameters are either known or that a training set is available.

• In the unsupervised case, we will have to infer both and from the observable entity .

Page 42: Segmentation In The Field Medicine

The MRF cont.

• There are many features that one can take as observation for the segmentation process: gray-level, color, motion, different texture features, etc.

• In our lesson we would be using a combination of classical, gray-level based, texture features and color, instead of direct modeling of color textures.

Page 43: Segmentation In The Field Medicine

Feature extraction

• For each pixel s, we define a vector , which represents the features at that pixel.

• The set of all the feature vectors form a vector field:={ | s S}, S = { (pixels).And as you remember, is the Observation, and will be the input of the MRF segmentation algorithm.

Page 44: Segmentation In The Field Medicine

Notes

• REMINDER: our features will be texture and color.

• We use the CIE-L*U*V color plane, so regions will be formed where both features are homogeneous while boundaries will be present where there is discontinuity in either color or texture.

Page 45: Segmentation In The Field Medicine

CIE-L*u*v* VS. RGB

CIELUV color histogram

RGB color histogram

Page 46: Segmentation In The Field Medicine

The Markov Random Field Segmentation Model

• Lets start by defining :

• We defined in a way that it represents the simple fact that segmentation should be locally homogeneous.

Let’s call this SQUIRREL

Page 47: Segmentation In The Field Medicine

Definitions

• = The number of possible cartoons.

• = The label of pixel s

Page 48: Segmentation In The Field Medicine

And now… the FUN part !!

• Don’t listen to me, just RUN!

Page 49: Segmentation In The Field Medicine

The Image Process

•We assume follows a normal distribution N(

Page 50: Segmentation In The Field Medicine

The Image Process cont.

• n = The dimension of our color-texture space.

• = A pixel class.

• = The mean vector (The average of all the feature vectors within the class ).

• = The covariance matrix, which describes the correlation between each two features in a given class.

Page 51: Segmentation In The Field Medicine

IntuitionOur feature vectors would look like this:

(1902180)

(2202220) (10535) (1046140 )

1

2 3

4

(2052200) (20530)

(30525)

5

6 (1306140)

(1176140)�⃗�1 �⃗�2 �⃗�3

Page 52: Segmentation In The Field Medicine

Intuition cont.

• For example: if we want to include vector 1 in class then: would be a very small number, and so is very low.

• If we include vector 5 in class then would be a big number and would be high.

Page 53: Segmentation In The Field Medicine

The Image Process cont.

•We assume each pixel feature is independent, and so:

Let’s call this CATLet’s call this DOG

Page 54: Segmentation In The Field Medicine

Fun Equations cont.

• REMINDER: (but we drop P))

Page 55: Segmentation In The Field Medicine

Fun Equations cont.

• REMINDER: We need to find that MAXIMIZES this expression.

• Or, equivalently, we need to find that MINIMIZES the expression inside the “-”.

Page 56: Segmentation In The Field Medicine

MINIMIZATION

• There are two main methods used to minimize our expression:1) ICM (Iterated Conditional Modes).2) Gibbs sampler.

• In some of the results we would be comparing those two methods.

Page 57: Segmentation In The Field Medicine

Parameter estimation

• There are some parameters in our equations that should be estimated, with or without supervision:1) If a training set is provided, then those parameters can be easily calculated based on the given data.2) If we do not have such a training set, we would have to use an iterative EM algorithm.

Page 58: Segmentation In The Field Medicine

Supervised Parameter Estimation cont.

•We can estimate by summing the vectors of class in the given dataset (and normalize the result).

•We can estimate by summing for every vector of class (and normalize the result).

Page 59: Segmentation In The Field Medicine

Unsupervised Parameter Estimation cont.

•When no dataset is available we would be using the Estimation Maximization for Guassian Mixture Identification.

• Our goal is to find parameter values which maximize the normalized log-likelihood function (which is a concave function).

Page 60: Segmentation In The Field Medicine

The EM Algorithm

• E step: compute a distribution on the labels based on the current parameter estimates.

• M step: calculating the parameters again based on the new labels, very similar to the supervised case.

• We repeat those two steps until convergence.

• K-Means is a specific case of the EM algorithm.

• The EM approach is similar to the Gradient Descent.

Page 61: Segmentation In The Field Medicine

MRF Results (Supervised)Texture Color Combined

ICM

Gibbs Sampler

Page 62: Segmentation In The Field Medicine

MRF Results (Unsupervised)Texture Color Combined

ICM

Gibbs Sampler

Page 63: Segmentation In The Field Medicine

The Finale

• Segmentation in the medicine field covers many topics and methods, today we covered 2 of them, saw some results and introduced a small estimation algorithm widely used in those topics.

Thank You For Listening!!

Page 64: Segmentation In The Field Medicine

References

• A Markov random field image segmentation model for color textured images. –Zoltan Kato, Ting-Chuen Pong.

• Medical Image Segmentation . –Xiaolei Huang, Gavriil Tsechpenakis.

• Deformable Model-Based Medical Image Segmentation. –Gavriil Tsechpenakis.

• http://en.wikipedia.org/wiki/Markov_random_field

• Saar Arbel’s presentation about snakes.

• http://en.wikipedia.org/wiki/Expectation%E2%80%93maximization_algorithm