3D Segmentation of Rodent Brain Structures Using Active Volume Model With Shape Priors

1. 3D Segmentation of Rodent Brain Structures Using Active Volume Model With Shape Priors Shaoting Zhang1, Junzhou Huang1, Mustafa Uzunbas1, Tian Shen2, Foteini Delis3, Xiaolei Huang2, Nora Volkow3, Panayotis Thanos3, Dimitris Metaxas1 1 CBIM, Rutgers, The State University of New Jersey, Piscataway, NJ, USA 2 Computer Science and Engineering Department, Lehigh University, PA, USA 3 Brookhaven National Laboratory, NY, USA

2. Motivations • Rodents are often used as models of human disease. • Use Magnetic Resonance Microscopy (MRM) to get 3D image for rodent brain. • 3D segmentation of brain regions based on MR images of the rodent brain. • Deformable model based segmentation.

3. Motivations • Three challenges: 1) unclear boundary, 2) complex textures, 3) complex shape.

4. Relevant work • Deformable model based segmentation • Deformable Models with Smoothness Constraints • Active contour [M. Kass, IJCV’88] • Gradient Vector Flow [C. Xu, TIP’98] • Deformable Superquadrics and Metamorphs [Metaxas 91,92; Huang, 08] • Priors from training data • ASM [T.F. Cootes, CVIU’95] • 3D ASM [Y. Zheng, TMI’08]

5. Proposed method-Framework Offline Learning Training Shapes Geometry Processing Shape Registration PCA Shape Statistics Runtime Segmentation System Input Image Image Alignment Volumetric Deformation Shape Constraint Result

6. Proposed method-Build Shape Statistics • Geometry processing (decimation, detail-preserved smoothing) Nealen, et.al.: LMO, GRAPHITE’06

7. Proposed method-Build Shape Statistics • Shape registration using AFDM … Shen, et.al.: AFDM, TMI’01

8. Proposed method-Build Shape Statistics • PCA analysis (mean and variance) Cootes, et.al.: ASM, CVIU’95

9. Proposed method-Deformation module • Evolution of probability density function computed from region information Huang, et.al.: Metamorphs, PAMI’08

10. Proposed method-Deformation module • 3D Finite Element Method (A3D·V=LV) Metaxas 92, Shen, et.al.: Active Volume Model, CVPR’09

11. Proposed method-Deformation module A3D (smoothness) Sorkine, et.al.: Laplacian Mesh Processing, EG’05

12. Proposed method-Framework, revisit Initialization Mean Mesh Input Image Image Alignment Initialization Reference Image Deformation Shape Statistics 3D Metamorphs (AVM) ASM Shape Refinement Result

13. Experiments • Settings • Adult male Sprague-Dawley rats • 21.1T Bruker Biospin Avance scanner • FOV of 3.4 × 3.2 × 3.0mm, voxel size 0.08mm • Data: 2/3 training and 1/3 for testing • All normal cases • Segment the cerebellum, the left and right striatum. • C++ and Python2.6 and tested on a 2.40 GHz Intel Core2 Quad computer with 8G RAM.

14. Experiments • Cerebellum (complex texture and shape details) Our method No prior

15. Experiments • Striatum (unobvious boundaries) Our method No prior

16. Experiments • p: sensitivity; q: specificity; DSC: dice similarity coefficient; RE-V: relative error of volume magnitude. 2TP/(2TP+FP+FN) TN/(TN+FP) TP/(TP+FN)

17. Conclusions • Proposed a segmentation framework using 3D Metamorphs based deformation module and ASM based shape prior module. • It is particularly useful when there are a limited number of training samples. • In the future, we will test this algorithm on a larger dataset and also investigate how to segment multiple structures simultaneously and effectively.

18. Thanks