+ All Categories
Home > Documents > 3D Digital Cleansing Using Segmentation Rays

3D Digital Cleansing Using Segmentation Rays

Date post: 02-Feb-2016
Category:
Upload: reed
View: 27 times
Download: 0 times
Share this document with a friend
Description:
3D Digital Cleansing Using Segmentation Rays. Authors: Sarang Lakare, Ming Wan, Mie Sato and Arie Kaufman Source: In Proceedings of the IEEE Visualization Conference, pp.37–44, 2000 Speaker: Wen-Ping Chuang Adviser: Ku-Yaw Chang. Outline. Introduction - PowerPoint PPT Presentation
Popular Tags:
35
3D Digital Cleansing Using Segmentation Rays Authors: Sarang Lakare, Ming Wan, Mie Sato and Arie Kaufman Source: In Proceedings of the IEEE Visualization Conference, pp.37– 44, 2000 Speaker: Wen-Ping Chuang Adviser: Ku-Yaw Chang 111/07/04 1
Transcript
Page 1: 3D Digital Cleansing Using Segmentation Rays

3D Digital CleansingUsing Segmentation Rays

Authors: Sarang Lakare, Ming Wan, Mie Sato and Arie KaufmanSource: In Proceedings of the IEEE Visualization Conference, pp.37–44, 2000Speaker: Wen-Ping ChuangAdviser: Ku-Yaw Chang

112/04/22 1

Page 2: 3D Digital Cleansing Using Segmentation Rays

Outline

Introduction Segmentation approach Result Conclusion

112/04/22 2

Page 3: 3D Digital Cleansing Using Segmentation Rays

Introduction(1/6)

Virtual screening techniques Volume rendering techniques have grown rapidly Interactive frame rates generate accurate results

Organs have complex structures Segmentation plays a very important role

112/04/22 3

Page 4: 3D Digital Cleansing Using Segmentation Rays

Introduction(2/6)

Segmentation Simple threshold

Get complicated due to partial volume effect Cause unwanted and non-existing surfaces

Combine the threshold

and flood-fill techniques Flexible Segmentation rays Volumetric contrast

enhancement112/04/22 4

Page 5: 3D Digital Cleansing Using Segmentation Rays

Introduction(3/6)

Polyps Potentially cancerous More than 5 mm

Consider potentially malignant Need to be removed

112/04/22 5

Page 6: 3D Digital Cleansing Using Segmentation Rays

Introduction(4/6)

Physical colon cleansing Large amounts of liquids Medications Enemas

112/04/22 6

Page 7: 3D Digital Cleansing Using Segmentation Rays

Introduction(5/6)

A friendly virtual colonoscopy system Bypass the colon physical cleansing Need for segmenting the residual material Give a clean colon to the rendering algorithm

112/04/22 7

Page 8: 3D Digital Cleansing Using Segmentation Rays

Introduction(6/6)

A new bowel preparation scheme Enhance the stool and fluid densities Take and reconstruct into a 3D dataset Partial volume effect

Have not a clear boundary Worsen situation

Finite resolution Low contrast

112/04/22 8

Page 9: 3D Digital Cleansing Using Segmentation Rays

Outline

Introduction Segmentation approach Result Conclusion

112/04/22 9

Page 10: 3D Digital Cleansing Using Segmentation Rays

Segmentation approach

Threshold Morphological operations Proposed approach

112/04/22 10

Page 11: 3D Digital Cleansing Using Segmentation Rays

Threshold

Human abdomen High density materials

Bone Fluid Stool

Soft tissue Air

112/04/22 11

Page 12: 3D Digital Cleansing Using Segmentation Rays

Threshold

Disadvantages Not remove PVE voxels Sensitive for each range of intensities Gives rise to aliasing effects at the inner colon

boundary

112/04/22 12

Fig.1 Fig.2 Fig.3

Page 13: 3D Digital Cleansing Using Segmentation Rays

Segmentation approach

Threshold Morphological operations Proposed approach

112/04/22 13

Page 14: 3D Digital Cleansing Using Segmentation Rays

Morphological operations

Succession operation Such as dilation and erosion Flood-fill on all the fluid and stool regions A sequence of dilates and erodes to remove the

PVE voxels

112/04/22 14

Page 15: 3D Digital Cleansing Using Segmentation Rays

Morphological operations

Dilation The dilation of A by B

B is the structuring element

112/04/22 15

Page 16: 3D Digital Cleansing Using Segmentation Rays

Morphological operations

Erosion The Erosion of A by B

B is the structuring element

112/04/22 16

Page 17: 3D Digital Cleansing Using Segmentation Rays

+

+

Morphological operations

Highly twisted affect the inner contour of the colon Dilate followed by erode

Can fill in holes Erode followed by dilate

Can remove noise

112/04/22 17

Page 18: 3D Digital Cleansing Using Segmentation Rays

Morphological operations

Disadvantages Task considering the large number of such

regions Require a lot of human intervention Slow down the entire process of segmentation Result in some fluid/stool regions being ignored

112/04/22 18

Page 19: 3D Digital Cleansing Using Segmentation Rays

Segmentation approach

Threshold Morphological operations Proposed approach

112/04/22 19

Page 20: 3D Digital Cleansing Using Segmentation Rays

Proposed approach

Approximate intensity based classification Classify the intensity values in the histogram

Depend on the number and type of district regions Region boundaries

Define by approximate thresholds Flexible

Unique intensity profiles at different intersections Study and store

112/04/22 20

Page 21: 3D Digital Cleansing Using Segmentation Rays

Proposed approach

Approximate intensity based classification

112/04/22 21

Page 22: 3D Digital Cleansing Using Segmentation Rays

Proposed approach

Region growing Detect and mark the interior AIR region

A smooth horizontal surface due to gravity Take a seed point to mark all the air voxels Reach no longer belong the air voxels

112/04/22 22

Page 23: 3D Digital Cleansing Using Segmentation Rays

Proposed approach

Selecting starting points for segmentation rays Critical to the overall speed of the algorithm Select fewer the voxels get faster the algorithm Assign the boundary voxels are simplest and

fastest

112/04/22 23

Page 24: 3D Digital Cleansing Using Segmentation Rays

Proposed approach

Detecting intersections using segmentation rays Critical to the detection of the polyps Remove most of the PVE voxels Give an improved colon contour

112/04/22 24

Page 25: 3D Digital Cleansing Using Segmentation Rays

Proposed approach

Segmentation rays From each of the AIR boundary voxel 26-connected-neighbor directions Stop and ignore

Not find any intersection after traversing a certain distance

112/04/22 25

+

Page 26: 3D Digital Cleansing Using Segmentation Rays

Proposed approach

Volumetric contrast enhancement A programmed transfer function

Unwanted materials are removed Similar to contrast enhancement

A smooth transfer function Get no-aliasing boundaries Improve the quality of volume rendering

112/04/22 26

Page 27: 3D Digital Cleansing Using Segmentation Rays

Outline

Introduction Segmentation approach Result Conclusion

112/04/22 27

Page 28: 3D Digital Cleansing Using Segmentation Rays

Result

Virtual colonoscopy system Automatic

Histogram classification Seed point detection

A fully automatic solution Segmentation Digital colon cleansing

112/04/22 28

Page 29: 3D Digital Cleansing Using Segmentation Rays

Result

Crux of this paper algorithm Characterizing the intersections

Accurate a result as a manual segmentation Not miss even a single intersection

112/04/22 29

Page 30: 3D Digital Cleansing Using Segmentation Rays

Result

A cross-section of the CT data showing colon

112/04/22 30

(L) (R)

Page 31: 3D Digital Cleansing Using Segmentation Rays

Result

Volume rendered images showing

112/04/22 31

(L) (R)

Page 32: 3D Digital Cleansing Using Segmentation Rays

Outline

Introduction Segmentation approach Result Conclusion

112/04/22 32

Page 33: 3D Digital Cleansing Using Segmentation Rays

Conclusion

Advantages Fast and accurate segmentation algorithm

Remove the partial volume effect General algorithm

Use by any application similar to virtual colonoscopy

112/04/22 33

Page 34: 3D Digital Cleansing Using Segmentation Rays

Conclusion

Future work Build an interactive segmentation system

Pick intersection characteristics using a mouse Find a particular intersection assigning

classification/reconstruction tasks to the rays Add visual feedback

Render and display the segmented dataset

112/04/22 34

Page 35: 3D Digital Cleansing Using Segmentation Rays

THE ENDThank you for listening

112/04/22 35


Recommended