Presentation is loading. Please wait.

Presentation is loading. Please wait.

NA-MIC National Alliance for Medical Image Computing NAMIC Engineering Activities September 8, 2005.

Similar presentations


Presentation on theme: "NA-MIC National Alliance for Medical Image Computing NAMIC Engineering Activities September 8, 2005."— Presentation transcript:

1 NA-MIC National Alliance for Medical Image Computing http://na-mic.org NAMIC Engineering Activities September 8, 2005

2 National Alliance for Medical Image Computing http://na-mic.org Results from Summer 2005 Programming Week at MIT… Applications –Quantitative Fiber Tract AnalysisQuantitative Fiber Tract Analysis –Rule-based DLPFC SegmentationRule-based DLPFC Segmentation –Non-Rigid EPI RegistrationNon-Rigid EPI Registration Algorithms –Shape DescriptionShape Description –Shape AnalysisShape Analysis –Bayesian SegmentationBayesian Segmentation –2d/3d point-landmark Detection2d/3d point-landmark Detection –Editing 3D Adaptive Tetrahedral Mesh GenerationEditing 3D Adaptive Tetrahedral Mesh Generation –Flux DiffusionFlux Diffusion Software Infrastructure –ITKuITKu –NRRD IONRRD IO –Slicer DTMRI Nightly TestingSlicer DTMRI Nightly Testing –LONI Pipeline Integration of UNC Shape Analysis PipelineLONI Pipeline Integration of UNC Shape Analysis Pipeline –Large Scale Algorithm Job Submissions via CondorLarge Scale Algorithm Job Submissions via Condor –Slicer 3.0 ArchitectureSlicer 3.0 Architecture

3 National Alliance for Medical Image Computing http://na-mic.org Quantitative Fiber Tract Analysis: Develop algorithms and tools for processing DTI data quantitatively via tractography Casey Goodlett, UNC (algorithms) Isabelle Corouge, UNC (algorithms) Mahnaz Maddah, MIT (algorithms) Xiaodong Tao, GE (software) Andrea Bewels, BWH Algorithms: 1.Work with slicer developers/users to get perspective on different approaches to tractography and fiber tract analysis. 2.Improve fiber clustering technique using normalized cut algorithm 3.Generic tensor statistics module Software: computational speed. Compatibility with BIRN data and slicer fiber format.. Clinical: Validation of results and feedback on methods. Input on requirements of future methods. Plan/Expected Challenges Team Accomplished by end of Programming Week (Add picture to illustrate accomplishment) 1)Successful processing of NA-MIC data 2)Conversion tool for fiber files 3)Collaboration with Slicer team 4)ITK module for Normalized Cut 5)Discussion with Tom Fletcher on Tensor Statistics

4 National Alliance for Medical Image Computing http://na-mic.org DLPFC Semi-automatic Segmentor: With minimal user interaction, this rule-based algorithm will segment the DLPFC from an input volume. This is a Slicer project but may have components that are appropriate for ITK. Ramsey Al-Hakim, GT (algorithms) (contact) John Melonakos (algorithms) Alex Yarmakovich, Isomics (software) Jim Fallon, UCI (clinical) Algorithms: start with the Matlab implementation and port to Slicer then explore porting to ITK. Software: computational speed. Intuitive user interface. Clinical: Validation of results. Plan/Expected ChallengesTeam Accomplished by end of Programming Week Build Slicer user interface. Final Step: Wrap ITK Bayesian Classifier Filter in VTK, and add to module.

5 National Alliance for Medical Image Computing http://na-mic.org EPI to MR Registration: Develop software tool which can perform robust non-rigid, intrasubject registration between an EPI image and a conventional structural image. Dave Tuch, MGH (algorithms) (contact) Josh Snyder, MGH (algorithms) Sandy Wells, BWH (algorithms consultant) Luis Ibanez, Kitware (software) Andy Saykin, Dartmouth (clinical) Algorithms: Write testing harness for validation of results. Identify suitable registration method available in ITK and optimal parameters. Refine as necessary Software: Provide guidance on optimal use of ITK reg methods. Clinical: Validation of results. Plan/Expected ChallengesTeam Accomplished by end of Programming Week Motivated fuller support for image orientation in Slicer and ITK Expanded understanding of metric and optimizer parameters Produced working rigid registration Identified possible approaches for non-rigid component

6 National Alliance for Medical Image Computing http://na-mic.org ITK based surface shape analysis modules: D evelop ITK tools for shape representation and statistical shape analysis. Ipek Oguz, UNC (Algorithms) Christine Xu, UNC (Algorithms) Martin Styner, UNC (Algorithms) (contact) Jim Miller, GE (software) Algorithms: Novel scientific visualization for verification and display of the results (distance maps, difference fields, covariance ellipsoid fields, effect size maps, p-value maps etc). Support of SPHARM description in ITK. Software: Design support for novel classes in ITK Clinical: Evaluation in separate Project (UNC-LONI-pipeline) Plan/Expected ChallengesTeam Accomplished by end of Programming Week Design and initial implementation for SPHARM support in ITK, new MeshSource class, Readers/Writers for basic coefficient files, scalar attributed meshes (distance maps, p- value maps). Simple tool for AttributedMesh display.

7 National Alliance for Medical Image Computing http://na-mic.org Shape Analysis: Description &Framework Develop a generally applicable description for statistical shape analysis studies, as well as a computational framework. Tom Fletcher, Utah (Algorithms) Martin Styner UNC (software) (contact) Jim Miller, GE (software) Algorithms: Algorithms for DTI shape analysis in the proposed framework. Software: Design and implement the description for statistical shape studies, including populations, subjects and objects. Use in combintaion with a database and pipeline framework. Clinical: Shape analysis of DTI data Plan/Expected ChallengesTeam Accomplished by end of Programming Week Clear design for statistical studies and experiments using DART2 database system and LONI pipeline. Design of database API. Next step is implementation of database system.

8 National Alliance for Medical Image Computing http://na-mic.org Bayesian Classifier Image Filter: Utilizing the power of Bayes's Rule along with an edge-preserving, affine invariant noise remover, brain imagery can be successfully segmented into ‘N’ classes. John Melonakos, GT (algorithms) (contact) Luis Ibanez, Kitware (software) Algorithms: start with the implementation currently in Matlab, and port to ITK. Software: modify peripheral ITK components as necessary. Plan/Expected ChallengesTeam Accomplished by end of Programming Week Working ITK code in SandBox. Final Step (in progress): Port code to the ITK filter. Clinical: test by segmenting brain volumes into white, gray and background

9 National Alliance for Medical Image Computing http://na-mic.org 3D Adaptive Tetrahedral Meshing: Develop algorithm and ITK/Slicer software module for volumetric adaptive mesh generaton. Andriy Fedorov, BWH/College of William and Mary (CWM) (algorithms,software) (fedorov@bwh.harvard.edu) Nikos Chrisochoides, BWH/CWM (algorithms) Will Shroeder, Kitware (software) Simon Warfield, BWH (application consultant, clinical, algorithms) Algorithms: start with Red-green crystalline BCC algorithm [Molino], and uniform meshing framework currently available in ITK, and refine as necessary. Software: user interface, better use of existing ITK functionality, computational speed, Clinical: neurosurgery application/brain deformation - FEM non-rigid registration (evaluate within existing framework). Plan/Expected ChallengesTeam Accomplished by end of Programming Week (as of July 21, 2005) positioned the implementation within ITK hierarchy agreed on separation of refinement and smoothing finished migration of the code to the ITK classes performed preliminary tests for the application: works! implemented deformation routines with ITK FEM and PETSc software: submission to MICCAI Open source workshop clinical: submission to SPIE Medical Imaging in progress need to work more on surface quality

10 National Alliance for Medical Image Computing http://na-mic.org 2D/3D Landmark Detection Implement algorithm for automatic landmark detection, implement necesaary classes. Bryn Lloyd, BWH/ETH Zürich (algorithms) Simon Warfield, BWH (application consultant, clinical, algorithms) Algorithms: implement class to estimate local correlation matrix (or other structure tensor). Software: user interface, better use of existing ITK functionality, computational speed, Clinical: neurosurgery application/brain deformation - non-rigid registration. Registration validation(?) Plan/Expected ChallengesTeam Accomplished by end of Programming Week Wrote itk classes to: - calculate structure tensor - calculate cornerness measure from structure tensor. - find local maxima of the cornerness. Wrote test code: works.

11 National Alliance for Medical Image Computing http://na-mic.org Flux Diffusion in ITK Implement in ITK a specific version of anisotropic diffusion for noise removal. Karl Krissian (collaborator) James Miller (GE) Algorithms: noise removal in 3D. Software: Implement the flux diffusion (currently as a module in the 3D slicer) in ITK. Clinical: noise removal as preprocessing to segmentation. Plan/Expected ChallengesTeam Accomplished by end of Programming Week Implemented the itkFluxDiffusion filter, consisting of the Following new classes: itkFluxAnisotropicDiffusionFunction.h itkFluxAnisotropicDiffusionFunction.txx itkFluxAnisotropicDiffusionImageFilter.h itkFluxAnisotropicDiffusionImageFilter.txx

12 National Alliance for Medical Image Computing http://na-mic.org Intensity Correction Port non-ITK code to ITK Neil Weisenfeld BWH (algorithms/software) Simon Warfield, BWH (algorithms) Algorithms: 1.Previously developed intensity correction (inhomogeneity artifact correction) and intensity normalization (standardization to a model) algorithms. 2.Pick most suitable optimization algorithm. Might require a parameterized representation for the correction field. Software: 1.Start with intensity correction as well-known problem 2.Once working, abstract into common framework between the two methods and code the normalization. Plan/Expected Challenges Team Accomplished by end of Programming Week (Add picture to illustrate accomplishment) Verified that the algorithm meets a need not currently in ITK (current method known not to work on neonatal data). Recoded our “production code” to use the ITK I/O framework. Initial ITK version as an ITK application. Needs some features added and needs to be recoded neatly as a separate class. Place your picture/movie here.

13 National Alliance for Medical Image Computing http://na-mic.org ITKu: Minimalist command line tools using ITK. Raul San Jose, BWH (collaborator) (contact) Gordon Kindlmann, BWH (collaborator) Jim Miller (GE) Algorithms: N/A. Software: nD array manipulation and pipeline communication between ITK filters. Clinical: Command line versatility to accomplish tasks. Plan/Expected ChallengesTeam Accomplished by end of Programming Week - Teem builds with Cmake - Define strategy for itku - Filter example: dynamic loading of itkDiscreteGaussianImageFilter U

14 National Alliance for Medical Image Computing http://na-mic.org Large Scale Algorithm Job Submission via Condor : Enable distributed execution of NAMIC algorithms. Jason Gerk, UCSD (Grid Infrastructure) (contact) Jeffrey Grethe, UCSD (Grid Infrastructure) Steve Pieper, BWH (Grid Applications) NAMIC Community Grid Infrastructure : Deploy the infrastructure and software to enable the scheduling and submission of staged NAMIC algorithms. NAMIC Communit y: Collect use cases and requirements as to how this infrastructure can be utilized by NAMIC developers and researchers. Plan/Expected ChallengesTeam Accomplished by end of Programming Week Scalability : Under heavy usage, monitor connections and performance. The discovered bottlenecks will aid in configuration improvements for specific implementations. Grid Applications : Application of the infrastructure to specific NAMIC algorithms. Gained understanding of how NAMIC would like to submit jobs. Different that how Condor works out of the box, so we'll have to customize for NAMIC community. Worked with Steve to draft 'Straw Man' for proposed design of 'namic-submit' functionality and syntax. Should handle proxy, submission, required files, logs, stdout, stdin, and job tracking. Built sample shell script that can be run command line which handles automatic job submission by creating submit files (and multiple submissions) and passing arguments into executable. Built preliminary shell scripts that when passed to cluster node will download datasets and executable, run program, and push results back into BIRN. Ran actual tests using NAMIC datasets and Registration executable. Uncovered a few global configuration issues for Compute Cluster (non-UID, memory, versions).

15 National Alliance for Medical Image Computing http://na-mic.org Gordon Kindlmann, BWH Raul San Jose Estepar, BWH Bill Lorensen, GE ? 1.Cvs commit latest NrrdIO into ITK (so that new “measurement frame” field for DWI can be parsed) 2.Make Slicer parse updated DWI NHDR headers 3.Help others w/ DWI data write NHDR headers 4.Mapping from the NRRD fields to ITK image fields 5.Experiment with Measurement Frame in ITK Image  Have to learn more about ITK Software: ITK Image data structures Clinical: save the children Plan/Expected Challenges Team Accomplished by end of Programming Week 1.Latest NrrdIO now committed into ITK; orientation info properly handled 2.Slicer can parse updated DWI NHDR headers (but via a VTK, not ITK, reader) 3.Rough spec of needs for DWI ITK Image type; working with Karthik Krishnan and others to get this implemented NrrdIO + measurement frames: Update NrrdIO in ITK and possibly add a measurement frame to ITK TODO: Mapping NRRD ITK non-scalar images Experiment with Measurement Frame in ITK

16 National Alliance for Medical Image Computing http://na-mic.org DTMRI Nightly Testing: Write nightly regression tests for the DT-MRI Slicer module, for as much existing code as possible. Lauren O’Donnell (MIT) (contact) Raul San-Jose Estepar (BWH) Kathryn Hayes (BWH) Steve Pieper (BWH) Andy Cedilnik, Kitware (software) Mark Dreusicke, BWH (clinical) Algorithms: Write testing code for many functions, including: Tensor creation Scalar measure creation Clustering I/O Software: Provide guidance on CTest and CMake, test data creation, and error reporting. Clinical: This project will help validate “research use only” of the DTMRI module. Plan/Expected ChallengesTeam Accomplished by end of Programming Week Some functioning tcl and C++ nightly tests (depends on slicer test process also). Clearly-defined requirements for when tests are added (“rules”). Clearly understood method for adding new tests. Documentation of above requirements and methods.

17 National Alliance for Medical Image Computing http://na-mic.org LONI Pipeline for UNC shape analysis: Move the UNC script based shape analysis pipeline to the LONI pipeline for enhanced applicability. Martin Styner, UNC (Algorithms) (contact) Ipek Oguz, UNC (Algorithms) Jags Rajendiran, UCLA (software) Algorithms: Use the existing algorithms and fit them into the LONI pipeline architecture. Software: If needed, any adaptations are made. Clinical: Validation of results from both UNC based pipeline to LONI pipeline applied to NAMIC Harvard VA caudate dataset. Plan/Expected ChallengesTeam Accomplished by end of Programming Week Pipeline constructed and validated on individual datasets Feature necessity and bug report list for LONI Combination of LONI and UNC Software Results from pipeline validated

18 National Alliance for Medical Image Computing http://na-mic.org Slicer3 Architecture Discussion: develop a user and developer friendly application environment All (algorithms) All (software) Presenters: Ron Kikinis, Steve Pieper, Mike Halle, Tina Kapur, Will Schroeder, Berk Geveci, Mike Pan, Bill Lorensen, Luis Ibanez All (clinical) Algorithms: express needs for rapid development, exerpimentation, and interactive steering/visualization Software: flexible software framework, easy to use Clinical: friendly user interface, full featured Plan/Expected ChallengesTeam Discussions : Big Picture, Technical, Developer Empowerment, Reuse, KWWidgets, 3D Widgets, Server Manager, Pipeline, Grid, Licneses… Plans: * Algorithm Wrapping (see next page).see next page * Widget “Bake Off” * Initial Focus on Image Viewer / Segmentation Editor

19 National Alliance for Medical Image Computing http://na-mic.org User Desktop Slicer 3.0 AlgorithmsITKVTK Slicer Modules VTK Apps Using ITK Scripts of Slicer Mods Batch Programs Non-NAMIC Cmd tools LONI Pipeline Birn Grid Data/Compute Slicer 3.0

20 National Alliance for Medical Image Computing http://na-mic.org Non-Programming Week NA- MIC Engineering Interactions Registration –Linear and Non-Linear vtkITK Registration Modules Now Available in Slicer I/O –vtkITK based Generic Readers in Slicer –vtkNRRDReader handles measurement frames, space directions, gradients for DWI fMRI –ITK Statistics framework underway Editor –Collaboration with Simbios NCBC at Stanford to adapt Slicer Editor for Musculoskeletal MRI


Download ppt "NA-MIC National Alliance for Medical Image Computing NAMIC Engineering Activities September 8, 2005."

Similar presentations


Ads by Google