Segmentation of 3D Medical Objects by Deformable M-reps

© Copyright UNC, 2001

Papers

Pizer SM, Chen J, Fletcher PT, Fridman Y, Fritsch DS, Gash AG, Glotzer JM, Jiroutek MR, Joshi S, Muller KE, Thall A, Tracton G, Yushkevich P, Chaney EL, (2001). Deformable M-Reps for 3D Medical Image Segmentation. Submitted for special UNC MIDAG issue of IJCV. [Adobe Acrobat Reader PDF format]

Pizer SM, Fritsch DS, Yushkevich P, Johnson V, Chaney EL (1999). Segmentation, Registration, and Measurement of Shape Variation via Image Object Shape. IEEE Transactions on Medical Imaging, 18 (10): 851-865.  [Adobe Acrobat Reader PDF format]

Related Topics

3D Segmentation by Deformable M-reps

• Recent IPMI'2001 publications related to M-Reps modeling:
• Intuitive, Localized Analysis of Shape Variability
• Multi-scale 3-D Deformable Model Segmentation Based on Medial Description
• Medial models incorporating object variability for 3D shape analysis
• Object-based image analysis at multiple scales: TBD

Radiotherapy Treatment Planning via Deformable M-reps Segmentation

• 2D Automatic Segmentation of Lung in Electronic Portal Image

 

Note: you may click on this image to play the movie but GIF animations play faster and smoother if you copy it to your local disk and play it from there. Use "Save Target As..." or "Save Link As..."

• Segmentation of Single-Figure Objects by Deformable M-reps

Statistical Shape Characterization for Neuroscience

• Shape of subcortical brain structures in schizophrenia from MRI: New results and background data
 
 
 
 
 
 
 
 
 
 
 


Topics

Why do we need shape (or is volume good enought) ? An example of a lateral ventricle shape analysis. Statistical analysis of lateral ventricles in Mono/Di-zygotic twins, volume and shape
New boundary based model for hippocampus with biological variability (pooled schizophrenia/control population) -> Sean Ho
Methods and Application of a medial model incorporating shape variability present in a population of similar shapes. Application of local shape analysis in hippocampi and lateral ventricles are presented.
Guido's paper with Martha Shenton about Shape difference in Hippocampus-amygdala complex
Gerig, G, M Styner and J Lieberman (2001). Shape versus Size: Improved understanding of the morphology of brain structures. Proc. MICCAI2001, to appear October 2001, Kluver.

• Recent IPMI'2001 submissions related to M-Reps modeling:
• Medial models incorporating object variability for 3D shape analysis

(extended Technical report version)

Additional Results

Kidney Results

1. Movie of the rigid registration and atom deformation (segmentation) sequence to extract a kidney from a 3D CT data set:

  RP(212K), AVI(3.6M), GIF(375K), AVI( 35M)
2. Movies of image slices vs. segmented kidneys for results which segmented successfully fully automatically after hand placement of model.

 

Stage	Kidney 2
During hand placement the user has full control	AVI(2.2M) AVI( 25M)
After hand placement	AVI(737K) AVI(8.1M)
After all m-rep stages: rigid registration, atom deformation	AVI(529K) AVI(5.8M)
After the boundary displacement, i.e., at the end of the segmentation	TBD

Movies of image slices vs. segmented kidneys for results which converged incompletely under automatic operation after hand placement of model
 

Stage	Kidney 5
After hand placement	AVI(698K) AVI(7.8M)
Failed initially to segment the kidney adequately: rigid registration, atom deformation	AVI(1.2M) AVI( 13M) [Note how much kidney is visible outside the model at the bottom.]
After repeating atom deformation with the previous automatic result as the model	AVI(897K) AVI(9.9M)

Cerebral Ventricle Results

Forming a model