1 / 31

Development and Dissemination of Robust Brain MRI Measurement Tools ( 1R01EB006733 )

Image Display, Enhancement, and Analysis. IDEA. Development and Dissemination of Robust Brain MRI Measurement Tools ( 1R01EB006733 ). Dinggang Shen. Department of Radiology and BRIC UNC-Chapel Hill. UNC-Chapel Hill - Dinggang Shen - 1/2 Postdoctoral fellow(s) UPenn

Download Presentation

Development and Dissemination of Robust Brain MRI Measurement Tools ( 1R01EB006733 )

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Image Display, Enhancement, and Analysis IDEA Development and Dissemination of Robust Brain MRI Measurement Tools (1R01EB006733) Dinggang Shen • Department of Radiology and BRIC • UNC-Chapel Hill

  2. UNC-Chapel Hill - Dinggang Shen - 1/2 Postdoctoral fellow(s) UPenn - Christos Davatzikos GE - Jim Miller - Xiaodong Tao Team

  3. Goal of this project • To further developHAMMER registration and white matter lesion (WML) segmentation algorithms, for improving their robustness and performance. • To design separate software modules for these two algorithms and incorporate them into the3D Slicer.

  4. Overview of Our Brain Measurement Tools • To further developHAMMER registration and WML segmentation algorithms, for improving their robustness and performance. • To design separate software modules for these two algorithms and incorporate them into the3D Slicer.

  5. HAMMER Matching attribute vectors Image registration and warping • Shen, et al., “HAMMER: Hierarchical Attribute Matching Mechanism for Elastic Registration”, IEEE Trans. on Medical Imaging, 21(11):1421-1439, Nov 2002. (2006 Best Paper Award, IEEE Signal Processing Society)

  6. Registration – HAMMER (1) Formulated as correspondence detection • Individual: • Model:

  7. How can we detect correspondences? Difficulty: High variations of brain structures Solution: Use both global and local image features to represent anatomical structures, such as using wavelets or geometrical moments. • Xue, Shen, et al., “Determining Correspondence in 3D MR Brain Images Using Attribute Vectors as Morphological Signatures of Voxels”, IEEE Trans. on Medical Imaging, 23(10): 1276-1291, Oct 2004.

  8. Distinctive character of attribute vector: toward an anatomical signature of every voxel Brain A Brain B Similarity Map Examples of attribute vector similarity maps, and point correspondences

  9. Voxels with distinct attribute vectors. Roots of sulci All boundary voxels Crowns of gyri HAMMER (2) Hierarchical registration – reliable points first To minimize the effect of local minima • Few driving voxels • Smooth approximation of the energy function • Many driving voxels • Complete energy function

  10. HAMMER (2) Hierarchical registration – reliable points first Beginning of registration End of registration

  11. 158 brains we used to construct average brain Template 158 subjects Average

  12. A subject before warping and after warping 3D renderings Model brain

  13. HAMMER HAMMER in labeling brain structures: Model Subject

  14. HAMMER - Cross-sectional views Model Subject

  15. Registration – HAMMER - Label cortical surface Inner cortical surface Outer cortical surface Model Subject

  16. Simulating brain deformations for validating registration methods Template Simulated • Xue, Shen, et al., “Simulating Deformations of MR Brain Images for Evaluation of Registration Algorithms”, Neuroimage, Vol. 33: 855-866, 2006.

  17. Successful applications of HAMMER: • 10+ large clinical research studies and clinical • trials involving >8,000 MR brain images: • One of the largest longitudinal studies of aging in the world to date, • (an 18-year annual follow-up of 150 elderly individuals) • A relatively large schizophrenia imaging study(148 participants) • A morphometric study of XXY children • The largest imaging study of the effects of diabetes on the brain to date, • (650 patients imaged twice in a 8-year period) • A large study of the effects of organolead-exposure on the brain • A study of effect of sustained, heavy drinking on the brain

  18. Improving: Learning Best Features for Registration • Criteria for selecting best-scale moments of each point: • Maximally different from those of its nearby points. • (Distinctiveness) • Consistent across different samples. (Consistency) • Best scales, used to calculate best-scale features, • should be smooth spatially. (Regularization) Best-scale moments: Moments w.r.t. scales: • Wu, Qi, Shen, “Learning Best Features for Deformable Registration of MR Brains”, MICCAI, 2005.

  19. Improving: Learning Best Features for Registration Results: • Visual improvement: Model Ours HAMMER’s • Average registration error: Histogram of deformation estimation errors • Wu, Qi, Shen, “Learning-Based Deformable Registration of MR Brain Images”, IEEE Trans. Med. Imaging, 25(9):1145-1157, 2006. • Wu, Qi, Shen, “Learning Best Features and Deformation Statistics for Hierarchical Registration of MR Brain Images”, IPMI 2007. Improved method HAMMER 0.66mm0.95mm

  20. Improving: Statistically-constrained HAMMER HAMMER Normal brain deformation captured from 150 subjects • Xue, Shen, et al., “Statistical Representation of High-Dimensional Deformation Fields with Application to Statistically-Constrained 3D Warping”, Medical Image Analysis, 10:740-751, 2006.

  21. Improving: Statistically-constrained HAMMER Results: • More smooth deformations: • Detection on simulated atrophy: HAMMER SMD+HAMMER

  22. White Matter Lesion (WML) Segmentation

  23. WML Segmentation • WMLs are associated with cardiac and vascular disease, and may lead to different brain diseases, such as MS. • Manual delineation • Computer-assisted segmentation • Fuzzy-connection • Multivariate Gaussian Model • Atlas based normal tissue distribution model • KNN based lesion detection • Lao, Shen, et al "Computer-Assisted Segmentation of White Matter Lesions in 3D MR images Using Support Vector Machine", Academic Radiology, 15(3):300-313, March 2008.

  24. Our approach • Image property: serious intensity overlap in WMLs T2 T1 WML PD FLAIR

  25. Attribute Vector • Attribute vector for each point v FLAIR PD T2 T1 Neighborhood Ω(5x5x5mm) • SVM To train a WML segmentation classifier. • Adaboost  To adaptively weight the training samples and improve the generalization of WML segmentation method.

  26. Overview of Our Approach Manual Segmentation Co-registration Skull-stripping Training SVM model via training sample and Adaboost Intensity normalization Training Pre-processing False positive elimination Voxel-wise evaluation & segmentation Testing Post-processing

  27. Results

  28. Results – 45 Subjects 10 for training, and 35 for testing • Paired Spearman Correlation (SC) Double • Coefficient of variation (CV) To investigate the variation of the lesion load’s distribution of the 35 evaluated subjects Defined as CV=/. Close • Lao, Shen, et al "Computer-Assisted Segmentation of White Matter Lesions in 3D MR images Using Support Vector Machine", Academic Radiology, 15(3):300-313, March 2008.

  29. Improvement in this project • Improve the robustness of multi-modality image registration (for T1/T2/PD/FLAIR) by using a novel quantitative and qualitative measurement for mutual information, where salient points will be considered more during the registration. • Design region-adaptive classifiers, in order to allow each classifier for capturing relative simple WML intensity pattern in each region; we will also develop a WML atlas for guiding the WML segmentation. • Lao, Shen, et al "Computer-Assisted Segmentation of White Matter Lesions in 3D MR images Using Support Vector Machine", Academic Radiology, 15(3):300-313, March 2008.

  30. Conclusion Further developHAMMER registration and WML segmentation algorithmsimprove their robustness and performance 3D Slicer

  31. Image Display, Enhancement, and Analysis IDEA Thank you! http://bric.unc.edu/IDEAgroup/ http://www.med.unc.edu/~dgshen/

More Related