Visual Computing Research @ CTI, DePaul University

1
Visual Computing Research _at_ CTI, DePaul
University

• Daniela Raicu
• Assistant Professor
• draicu_at_cs.depaul.edu
• http//facweb.cs.depaul.edu/research/vc

2
Visual Computing Group

• CTI Faculty
• Gian Mario Besana
• Lucia Dettori
• Jacob Furst
• Gerald Gordon
• Steve Jost
• Yakov Keselman
• Daniela Raicu

• Collaborators Department of Radiology,
  Northwestern University Northwestern Memorial
  Hospital, Chicago, IL
• Dr. David Channin, Chief of Informatics,
  Department of Radiology

3
Visual Computing Group

• Graduate Students
• John Campion, Ramzy Darwish
• William Horsthemke, Gabriel Sanchez, Winnie Tsang

• Undergraduate Students
• Stelian Aioanei, Andrew Corboy
• Jong Lee, Mikhail Kalinin
• Lindsay Semler, Dong-Hui Xu

• Visual Computing (VC) area
• CSC381/CSC481 Introduction to Image Processing
• CSC382/CSC482 Image Analysis and its
  Applications
• CSC384/CSC484 Introduction to Computer Vision
• VC research seminar Fall Quarter, Friday, 500 -
  600pm
• VC workshop Spring Quarter, Friday, April 15th ,
  2005
• Intelligent Multimedia Processing (IMP) lab
  http//facweb.cs.depaul.edu/research/vc

4
Research problems
Content-based Image Retrieval Image retrieval
systems that permit image searching based on
features automatically extracted from the images
own visual content are called content-based image
retrieval (CBIR) systems.
Domain-specific features - fingerprints, human
faces

• visual features
• (primitive or low-level image features)

General features - color, texture, shape
Drawback-lack of expressive power
5
Content-based Image Retrieval
Feature Extraction
Semantic Gap
?
Mountains and water-falls
It is a nice sunset.
Meaning Sunset
Text Database
6
Content-based Image Retrieval
Feature Representation Two examples of original
images and their representations.
7
Content-based Image Retrieval
Two examples of original images and their
representations
8
Content-based Image Retrieval
Similarity Measure
Image T
Image Q
, bi masking bit
9
Content-based Image Retrieval
Retrieval Results
Query
10
Content-based Image Retrieval
11
Content-based Image Retrieval
12
Medical Imaging
Problem statement Human body organs
classifications using raw data (pixels) from
abdominal and chest CT images.
13
Segmentation
Medical Imaging

• - Data 340 DICOM images
• Segmented organs liver (56), kidneys (55),
  spleen (39), backbone (140),
• heart (50)
• Segmentation algorithm Active Contour Mappings
  (Snakes)
• A boundary-based segmentation algorithm
• Input for the algorithm a number of initial
  points five main
• parameters that influence the way the boundary is
  formed.

14
Segmentation Matlab Demo
Advantage it detects complex shapes Disadvantage
it needs manual selection of the initial points
and of the parameters Our Solution perform
clustering of similar regions using a neural
network
15
Segmentation Examples
16
Segmentation Examples
17
Texture Analysis Classification
Organ/Tissue segmentation in CT images
IF HGRE lt 0.38 AND ENTROPY gt 0.43 AND SRHGE lt
0.20 AND CONTRAST gt 0.029 THEN Prediction
Heart Probability 0.99
18
Medical Imaging
Texture Analysis
Entropy
Energy
SumMean
Variance
Correlation
Cluster Tendency
Contrast
Homogeneity
Maximum Probability
Inverse Difference Moment
.034692
.6345745
2.764427
7.308909
11.662886
26.471211
.44697
.112929
.110921
3.892828
19
Medical Imaging
Texture Analysis
Entropy
Energy
SumMean
Variance
Correlation
Cluster Tendency
Contrast
Homogeneity
Maximum Probability
Inverse Difference Moment
.108713
.631435
6.224426
9.340897
13.628323
31.139159
.280289
.3081855
.0723125
3.4151415
20
Medical Imaging
Texture Analysis
Entropy
Energy
SumMean
Variance
Correlation
Cluster Tendency
Contrast
Homogeneity
Maximum Probability
Inverse Difference Moment
.055998
.5577785
3.49784
3.737737
14.278469
11.453111
.437988
.1250245
.1436305
3.38482
21
Medical Imaging
Texture Analysis
Entropy
Energy
SumMean
Variance
Correlation
Cluster Tendency
Contrast
Homogeneity
Maximum Probability
Inverse Difference Moment
.049172
.5369255
3.066407
1.634463
12.309719
3.471442
.460422
.0897425
.0377875
3.3099875
22
Medical Imaging
Texture Analysis
Entropy
Energy
SumMean
Variance
Correlation
Cluster Tendency
Contrast
Homogeneity
Maximum Probability
Inverse Difference Moment
.091388
.6208175
1.618982
0.912752
11.755226
2.032082
.506894
.1742075
.123976
2.72509
23
Texture Descriptors Matlab Demo
24
Organ/Tissue Classification
IF HGRE lt 0.38 AND ENTROPY gt 0.43 AND SRHGE lt
0.20 AND CONTRAST gt 0.029 THEN Prediction
Heart Probability 0.99
Algorithm - decision trees Output Decision
Rules Performance estimated using -
sensitivity - specificity Advantage Set of
decision rules that can be used for annotation
25
Organ/Tissue Classification
Examples of Decision Tree Rules for Combined
Data

• IF (HGRE lt 0.3788) (CLUSTER lt 0.0383095)
  (INVERSE lt 0.768085) (SUMMEAN lt 0.556015)
  (SRLGE lt 0.101655) (ENEGRY gt 0.106715)
• THEN Prediction Spleen, Probability 0.928571
  
• IF (HGRE lt 0.3788) (CLUSTER lt 0.0383095)
  (INVERSE lt 0.768085) (SUMMEAN lt 0.556015)
  (SRLGE gt 0.101655)
• THEN Prediction Liver , Probability 1.000000
  
• IF (HGRE lt 0.3788) (CLUSTER lt 0.0383095)
  (INVERSE lt 0.768085) (SUMMEAN gt 0.556015)
  (GLNU lt 0.087365)
• THEN Prediction Kidney, Probability 0.924658
  

26
Organ/Tissue Classification
Examples of Decision Tree Rules for Combined
Data

• IF (HGRE lt 0.3788) (CLUSTER gt 0.0383095)
  (GLNU gt 0.03184) (ENTROPY gt 0.433185) (SRHGE
  lt 0.19935) (CONTRAST gt 0.0295805)
• THEN Prediction Heart, Probability 0.988372
• IF (HGRE lt 0.3788) (CLUSTER gt 0.0383095)
  (GLNU lt 0.03184) (LRE lt 0.123405)
• THEN Prediction Backbone, Probability
  1.000000

27
Organ/Tissue Classification
Decision Tree Accuracy on Testing
Data (Co-occurrence, Run-length, and Combined)
ORGAN Sensitivity Specificity Precision Accuracy
Backbone 96 / 98 / 98 99 / 100 / 99 99 / 99 / 99 98 / 99 / 99
Liver 64 / 57 / 78 96 / 98 / 95 75 / 84 / 71 92 / 92 / 92
Heart 79 / 82 / 75 96 / 95 / 98 80 / 77 / 90 94 / 93 / 95
Kidney 89 / 89 / 89 96 / 93 / 96 80 / 67 / 77 94 / 92 / 95
Spleen 60 / 44 / 60 93 / 93 / 95 53 / 45 / 63 89 / 87 / 91
28
Tissue Classification Matlab Demo
29
Publications (CBIR)
1 Daniela Stan and Ishwar K. Sethi, Image
Retrieval using a Hierarchy of Clusters in
Lecture Notes in Computer Science Advances in
Pattern Recognition ICAPR 2001, Springer-Verlag
Ltd. (Ed), pp. 377-388, 2001. 2 Daniela Stan
and Ishwar K. Sethi, Mapping Low-level Image
Features to Semantic Concepts in Proceedings of
SPIE Storage and Retrieval for Media databases,
pp. 172-179, 2001. 3 Ishwar K. Sethi, Ioana
Coman, Daniela Stan, Mining Association Rules
between Low-level Image Features and High-level
Concepts in Proceedings of SPIE Data Mining and
Knowledge Discovery III, pp.279-290, 2001.
4 Daniela Stan and Ishwar K. Sethi, Color
Patterns for Pictorial Content Description, ACM
Symposium on Applied Computing, 2002. 5
Daniela Stan and Ishwar K. Sethi, eID A System
for Exploration of Image Databases, Information
Processing and Management Journal,2002. 6
Daniela Stan and Ishwar K. Sethi, Synobins An
intermediate level towards Annotation and
Semantic Retrieval, IEEE Trans. Multimedia
Journal.
30
Publications (MI)
1 D. Xu, J. Lee, D.S. Raicu, J.D. Furst, D.
Channin. "Texture Classification of Normal
Tissues in Computed Tomography", The 2005 Annual
Meeting of the Society for Computer Applications
in Radiology, June 2-5, 2005. (Submitted) 2
D.S. Raicu, W. Tsang, M. Kalinin, D. Xu, J.D.
Furst, D. Channin. "Automatic Tissue Context
Determination in Computed Tomography", SPIE
Medical Imaging, February 1217, 2005.
(Submitted) 3 D. H. Xu, A. Kurani, J. D.
Furst, D. S. Raicu, "Run-length encoding for
volumetric texture", The 4th IASTED International
Conference on Visualization, Imaging, and Image
Processing - VIIP 2004,  Marbella, Spain,
September 6-8, 2004. 4 D. Channin, D. S.
Raicu, J. D. Furst, D. H. Xu, L. Lilly, C.
Limpsangsri, "Classification of Tissues in
Computed Tomography using Decision Trees", Poster
and Demo, The 90th Scientific Assembly and Annual
Meeting of Radiology Society of North America
(RSNA04), November 28, 2004. 5 A. Kurani, D. H.
Xu, J. D. Furst, D. S. Raicu, "Co-occurrence
matrices for volumetric data", The 7th IASTED
International Conference on Computer Graphics and
Imaging CGIM, August 16-18, 2004 . 6 D. S.
Raicu, J. D. Furst, D. Channin, D. H. Xu, A.
Kurani, "A Texture Dictionary for Human Organs
Tissues' Classification", Proceedings of the 8th
World Multiconference on Systemics, Cybernetics
and Informatics (SCI 2004), July 18-21, 2004.
31
Daniela Raicu Intelligent Multimedia Processing
Laboratory School of CTI DePaul University THE
END!