You are on page 1of 10

Application of image processing

techniques to tissue texture


analysis and image compression
Advisor : Dr. Albert Chi-Shing CHUNG
Presented by Group ACH1
(LAW Wai Kong and LAI Tsz Chung)
Computer Science Final Year Project 2004
Overview
Introduction
Motivation
Objectives
Results
Classification algorithms:
Feature extraction & Classifier selection
Software implementation:
Conclusion
Future Extension
Question and Answer Session


I ntroduction - Motivation
Diagnosis of cirrhosis:

1) Manual diagnosis of ultrasonic liver image
2) Histological analysis
Invasive
Inaccurate
Results dependent on experience of sonographers
How about computer aided diagnosis system?
In what extent this system assist doctor?
- Objectives
1. Designated user interface with support of ultrasonic image
compression
No pre-image processing is needed
Reduce storage space
Facilitate the diagnosis process
2. Multi-severity level classification
Cirrhosis treatment require severity information.
3. Machine independence
Compatible with different ultrasound scanning machine
Challenge !!
How to classify patients?
2 steps
Step 1: Feature Extraction
Firstly, extract useful features from image.
We have examined several feature extraction approaches
for performance comparison
The most accurate approach will be implemented in our
system
1. Direct comparison of wavelet coefficient
(Haar, Symlets, Daubechies)
2. Histogram of wavelet coefficient
(Haar, Symlets, Daubechies)
3. Statistic with Difference on
Gaussians filter
4. Direct comparison between
multi-scale co-occurrence matrix
} ) , ( , ) , ( , ,
: )] , ( ), , {[(
1
) , (
j n m g i l k g dy n l dx m k
ROI n m l k y Cardinalit
N
j i C
= = = =
e =
5. Statistic with multi-scale approach and
co-occurrence matrix
Step 1: Feature Extraction
The six features:
1) The mean gray level

e
=
ROI j i
j i I
N
mean
) , (
) , (
1
- Inversely proportion to cirrhosis severity.
- Affected by the area of normal tumor
2) The first percentile of the gray level distribution P

=

=
s <
P
i
i
P
j
j
h h
0
1
0
10
1
First order statistic
- Inversely proportion to cirrhosis severity.
- Affected by the present of normal tumor
Co-occurrence matrix statistic
3) Entropy:

e
=
G j i
j i C j i C Entropy
,
)] , ( log[ ). , (
4) Contrast:

e
=
G j i
j i C j i Contrast
,
2
) , ( . ) (
5) Angular Second Moment:

e
=
G j i
j i C ASM
,
2
) , (
6) Correlation
y x
G j i
y x
S S
m m j i ijC
n Correlatio

e

=
,
) , (




=
=
=
=
i
y
j
y
j
x
i
x
i j
y
j i
x
m j i C j S
m j i C i S
j i C i j m
j i C i m
2 2 2
2 2 2
) , (
) , (
) , (
) , (
Features Relation of feature and
cirrhosis status
Physical meaning
Entropy Inversely proportion
Randomness of intensity
changes
Contrast Inversely proportion
Edge detection
ASM Inversely proportion
Homogeneity of image
Correlation Proportion
Similarity among pixel pairs
6) Morphological based method
Segment out tumor structure from liver
Count the number and circumference of tumor
Input features: normalized to range between [0,1]
Category: normalized to range between [0,1]
Classification: by setting thresholds base on # category.
1st layer: 5 hyperbolic tangent sigmoid transfer units
2nd layer: 1 linear transfer unit
Train function: Levenberg-Marquardt back-propagation
Performance: MSE
Stopping threshold: 0.01
Maximum training cycle = 200
Step 2: Classifier
Basic requirements:
Continuous learning
Multi class classification (severity category)
Robust
Database can update per patient (one pattern).
Secondly, classify patients based on extracted features
1) k-Nearest Neighbor Classifier
Use the category of k-nearest neighbor in database to
classify a new entry.
The features are normalized by standard score.
Distance-weighted.
Choice of distance: SSD / KLD
Physically, KLD measures relative entropy between PDF
2) Feed-forward Neural Network
A direct continuation of the work on Bayes classifiers,
which relies on Parzen windows classifiers.
Setting:
3) Probabilistic Neural Network
It learns to approximate the PDF of the training examples.
) (
1
/ ) 1 (
1
/ ) 1 (
2
2

=

=

> =
j
kj
k
ki
N
i
w x
N
i
w x
e e output
o
o


The input features are normalized by standard score.
Commonly used in image feature classification

=
) (
) (
log ) ( ) (
2
1
1 2 1
k p
k p
k p p p KLD
Evaluation of algorithms
Method of evaluating hypothesis: 10-fold cross validation (in MatLab)
Problem: Images of the same patient have similar features!
Solution: Use patient ID to partition the data set.
Problem: uneven class distribution in folds!
Solution: Partition the patients based on their category, ensure
class distribution is similar to original data set.
The features:
Theoretically, morphology is a descriptive feature,
but, practically, fine tuning of parameters is needed.
Segmentation parameter
(sigma of Gaussian filter, initial marker intensity)
too sensitive to suit all testing cases
Number of tumors was unreasonably fluctuated.
(tumors count ranged from 15 to 90)
Comparison of best results among all features sets with different classifier:
Features Set Classifier Accuracy
Type Setting Type Parameters
2 Class
Classification
3 Class
Classification
Plain wavelet
coefficient
3 Level
Haar
KNN K=5
301/732
41.1202%
234/732
31.9672%
Histogram of wavelet
coefficient
2 Level
Haar
kNN KLD, k=12
548/772
75.9003%
431/772
59.6953%
Statistic with
Difference on
Gaussians filter
Filtering
along X-
direction
kNN K=19
531/772
(72.541%)
434/772
(59.2896%)
PNN
447/772
(72.541%)
396/772
(54.0984%)
FFNN
497/772
(67.8962%)
442/772
(60.3825%)
Features Set Classifier Accuracy
Type Setting Type Parameters
2 Class
Classification
3 Class
Classification
multi-scale co-
occurrence matrix
3
Resolution
level
kNN KLD, k=3
312/515
60.5825%
219/515
45.5242%
SSD, k=2
284/515
55.1456%
211/515
40.9709%
Statistic of multi-
resolution and co-
occurrence matrix
2
Resolution
Level
kNN SSD, k=19
614/732
83.8798%
511/732
69.8087%
PNN
607/732
82.9235%
497/732
67.8962%
FFNN
619/732
84.5628%
508/732
69.3989%
The data set is captured by Dr. Simon Yu, consultant and adjunct associate professor from
Department of Diagnostic Radiology and Organ Imaging, Prince of Wales Hospital
Evaluation of algorithms
The classifiers:
Accuracy:
>>> all of them have similar results.
>>> Depends on features.
Running time (including partition for 732 testing cases):
Classifier 2 classes 3 classes
kNN 2s 2s
FFNN 67s 80s
PNN 7s 7s
Pros and Cons
k-NN
Fast
Easy to implement
Sensitive to class distribution of data set.
Size of database is large and linearly increasing.
FFNN
Size of database is a small constant.
Robust
Training is slow. (> 40 times of k-NN)
Should update per epoch to prevent noise.
PNN
Fast
Highly sensitive to class distribution of data set.
Size of database increases linearly.
k-NN
Conclusion
Developed a designated classification system that can
contribute to medical aspect
Examined different machine independent
classification algorithms for multi-severity
classification
Proposed utilization of multi-resolution statistic with
co-occurrence matrix for cirrhosis detection
Realized machine learning and image processing
techniques in a real life situation
Explored the knowledge about cirrhosis and liver
Future Extension
Clustering of features
Fine tuning the parameters of morphological
approach
Histological findings of cases will be able to
improve our system
Question and Answer Session

You might also like