????? t?t?? d?af??e?a?

1
A Comparative Study of Texture Features for the
Discrimination of Gastric Polyps in Endoscopic
Video
D. Iakovidis1, D. Maroulis1, S.A. Karkanis2, A.
Brokos1
1 University of Athens Department of
Informatics Telecommunications Realtime
Systems Image Processing Laboratory
2 Technological Educational of Lamia
Department of Informatics Computer Technology
2
Gastric Cancer Polyps

• Gastric Ca is the 2nd Ca-related cause of death
• Rarely alarming symptoms
• gt40 appear as polyps
• Gastric polyps are visible tissue masses
• protruding from the gastric mucosa
• Adenomatous polyps are usually precancerous
• Gastroscopy is a screening procedure with
• which polyp growth can be prevented

3
Aim
Medicine
Computer Science
Computer-Based Medical System (CBMS) to support
the detection of gastric polyps

• Increase endoscopists ability for polyp
  localization
• Reduction of the duration of the endoscopic
  procedure
• Minimization of experts subjectivity

4
Previous Works

• Detection of gastric ulser using edge detection
• (Kodama et al. 1988)
• Diagnosis of gastric carcinoma using
  epidemiological
• data analysis
• (Guvenir et al. 2004)

5
Previous Works

• Detection of colon polyps using texture
  analysis
• 1. Texture Spectrum Histogram (TS)
• (Karkanis et al, 1999) (Kodogiannis et al, 2004)
• 2. Texture Spectrum Color Histogram Statistics
  (TSCHS)
• (Tjoa Krishnan, 2003)
• 3. Color Wavelet Covariance (CWC)
• (Karkanis et al, 2003)
• 4. Local Binary Patterns (LBP)
• (Zheng et al, 2004)

6
Texture Spectrum Histogram
(Wang He, 1990)

• Greylevel images
• 3?3 neighborhood thresholded in 3 levels
• V0 central pixel, Vi neighboring pixels, i 1,
  2, 8
• Texture Unit TU E1, E2,, E8
• Totally 38 6561 possible TUs
• Feature vectors formed by the NTU distribution

7
Local Binary Pattern Histogram
(Ojala, 1998)

• Greylevel images
• Inspired by the Texture Spectrum method
• 3?3 neighborhood thresholded in 2 levels
• Totally 28 256 possible TUs
• Feature vectors formed by the NTU distribution

8
Texture Spectrum and Color Histogram Statistics
(Tjoa Krishnan, 2003)

• Color images (HSI)
• Inspired by the Texture Spectrum method
• Feature vectors formed by 1st order statistics
  on the
• NTU distribution in the I-channel
• Energy Entropy
• Mean, Standard deviation, Skew Kurtosis
• In addition color features ?C from each color
  channel C

9
Color Wavelet Covariance
(Karkanis et al, 2003)

• Color images (I1I2I3)
• Discrete Wavelet Frame Transform (DWFT)
• on each channel C
• Co-occurrence statistics F on each wavelet band
  B(k)
• Feature vectors formed by the Covariance of the
  
• cooccurrence statistics between the color
  channels

10
Experimental Framework

• We focus only on the textural tissue patterns
• Gastroscopic video 320?240 pixels
• Region of interest 128?128 pixels

11
Experimental Framework

• 1,000 Representative video frames
• Verified polyp and normal samples
• 4,000 non-overlapping sub-images 32?32 pixels

12
Experimental Framework

• Support Vector Machines (SVM)
• 10-fold cross validation
• Receiver Operating Characteristics (ROC)
• Accuracy assessed using
• the Area Under Characteristic (AUC)

13
Results
14
Results
15
Conclusions

• We have considered texture as a primary
• discriminative feature of gastric polyps
• Four texture feature extraction methods were
• considered
• Their performance was compared using SVMs
• and ROC analysis

16
Conclusions

• The development of a CBMS for gastric polyp
• detection is feasible
• Color information enhances gastric polyp
• discrimination
• The discrimination performance of the spatial
  and
• the wavelet domain color texture features is
• comparable
• The CBMSs developed for colon polyp detection
• can reliably be used for gastric polyp detection

17
(No Transcript)