2012 Summer Project Week:DifficultRegistration
Registration Result Visualization
Slicer:BRAINS
NiftyReg
SIFT Landmark
Key Investigators
- Erasmus Medical Center: Stefan Klein
- University College London: Marc Modat
- UNC: Aditya Gupta, Martin Styner
- BWH: Matthew Toews, Petter Risholm, Dominik Meier, William Wells
Objective
To identify solutions to difficult image registration problems that challenge the limits of current technology. Aspects of difficulty will include:
- inter-subject registration
- truncation, missing tissue
- unknown initialization
- inter-species registration
- articulated deformation
Approach, Plan
A set of difficult pair-wise registration problems will be considered. Participants will discuss workable solutions based on their expertise and background, and these solutions will be documented.
Registration cases can be found here.
- CT: atlas and torso have flipped orientation: Correction Xforms here: Flip CT atlas&torso, zip file with 2 .tfm files
Progress
We held a general discussion of registration challenges in the community. Results were generated for head and neck data (Ivan Kolesov), three registration approaches were evaluated on challenging head and body images: (NiftyReg), (Slicer:BRAINS), (SIFT Landmarks).
- Registration of difficult brain images is successful, body images remain challenging.
- Registration direction has an important impact, i.e. which images are designed as fixed or moving. Symmetric or bi-directional registration is helpful.
- Masking of problematic image regions, e.g. pathology, is an important but time-consuming pre-processing task that could be further investigated or automated. For instance, interactive masking/segmentation of pathology, linking registration and masking.
Delivery Mechanism
Attention Participants: Please log in and update/correct entries in the table below. For bonus points, please provide links or solutions to image registration problems on this page.
Participant | Affiliation | Context | Techniques | Solutions/Links |
---|---|---|---|---|
Steven Aylward | Kitware | CT, US, ressection, brain tumors, changing pathology, sliding organ | Sliding Geometry, Geometric Metamorphosis | |
Karl Diedrich | AZE | Rigid registration, abdomen | Multi-resolution registration | |
James Fishbaugh | SCI | Shape analysis and registration | ||
Aditya Gupta | UNC | DTI, enlarged lateral ventricles | ||
Stefan Klein | Erasmus Medical Center | General Registration | ||
Ivan Kolesov | Georgia Tech | Articulated, point-based registration | Plastimatch, NiftyReg | Head Neck Results |
Dominik Meier | BWH | General registration | Slicer: BRAINS | CT torso: FAILED |
Marc Modat | UCL | neuro-deg. diseases, longitudinal | NiftiReg | Some test res |
Albert Motillo | GE | Parsing CT, Detection | ||
Simrin Nagpal | Queens University | CT/US registration | ||
Samon Nuranian | UBC | US-guided intervension, spine | ||
Andre Remi | UCLA | Longitudinal changes in TBI, tissue types | ||
Peter Risholm | BWH | Brain, head and neck, radiation therapy | Probabilistic Uncertainty | |
Samira Sojoudi | UBC | Spine, CT/US registration | ||
Matthew Toews | BWH | General registration | SIFT landmark correspondence | |
Bo Wang | Utah | TBI image segmentation | ||
Kevin Wang | Princess Margaret Hospital | Adaptive radiation therapy, longitudinal | ||
William Wells | BWH | Interventional applications | Theory: Segmentation, Registration |
Links for Data
- Matt's initial examples
- Slicer Registration Case Library
- XCAT
- DTI Files Enlarged LV registration with normal control
- DWI Files Enlarged LV registration with normal control
- TBI Cases
- TumorSim longitudinal data: To appear at http://midas3.kitware.com
Links for Tools & Methods
- Sliding Geometries Registration: http://public.kitware.com/Wiki/TubeTK
- Geometric Metamorphosis: https://github.com/calaTK/calaTK
Links for Papers
- Sliding Geometries
- ISBI 2011: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3141338/
- Abdominal Imaging, MICCAI, 2011: http://www.springerlink.com/content/552824638l375645/
- Geometric MetaMorphosis