Summer ITKv4 ClinicalGroupMeetingNotes: Difference between revisions

From KitwarePublic
Jump to navigationJump to search
No edit summary
No edit summary
Line 24: Line 24:
== Lesion Sizing Toolkit ==
== Lesion Sizing Toolkit ==
<b>Inputs:</b> DICOM
<b>Inputs:</b> DICOM
<b>Outputs:</b> Lesion volume measurements and segmentations.
<b>Outputs:</b> Lesion volume measurements and segmentations.<br>
<b>Contributions:</b> Functioning toolkit.  Possibly new ITK filters classes.  Data.
<b>Contributions:</b> Functioning toolkit.  Possibly new ITK filters classes.  Data.
* Already in ITK as an external module.  Contract is to port to use ITKv4 and distribute.
* Already in ITK as an external module.  Contract is to port to use ITKv4 and distribute.
Line 39: Line 39:
== ITK Algorithms for Analyzing Time-Varying Shape with Application to Longitudinal Heart Modeling ==
== ITK Algorithms for Analyzing Time-Varying Shape with Application to Longitudinal Heart Modeling ==
<b>Inputs:</b> Segmentations
<b>Inputs:</b> Segmentations
<b>Outputs:</b> Point sets
<b>Outputs:</b> Point sets<br>
<b>Contributions:</b> New ITK module (particle system), filters, classes.
<b>Contributions:</b> New ITK module (particle system), filters, classes.
* Existing code base mostly ITK
* Existing code base mostly ITK

Revision as of 17:23, 27 June 2011

3D Real-Time Physics-Based Non-Rigid Registration for Image Guided Neurosurgery (PBMNRRegistration)

The following is a rough pipeline of the method with proposed classes.

Inputs: a segmentation mask, a mesh
Outputs: deformation field, transformed image(s)
Contributions: New filters, classes. Application?

  1. FeaturePointSelection3dFilter: No dependencies. Plan to start implementation with this filter.
  2. BlockMatching3Dfilter: Similar to Penn FEM registration classes? Perhaps only need to implement a new metric? Plan to use the GPU infrastructure, but also have a non GPU version.
  3. PBMSolver: PETSc dependence
  4. ImageWarp: Already in ITK

What support is needed?

  • CMake integration w/ PETSc and MPI. Build / distribution issues.
  • Further discussion and collaboration with the FEM, registration, and GPU groups.

Gaps:

  • Mesh generation. Tetmesh reader / converter? Use Biomesh3D and bridge to ITK?
  • Self-updating transform object
  • PETSc & MPI within an ITK filter?

Data:

  • ?

Lesion Sizing Toolkit

Inputs: DICOM Outputs: Lesion volume measurements and segmentations.
Contributions: Functioning toolkit. Possibly new ITK filters classes. Data.

  • Already in ITK as an external module. Contract is to port to use ITKv4 and distribute.
  • Using spatial objects as inputs and outputs

What support is needed?

  • Does ITK want a tighter integration of these classes, and in this same form? Does this cover more general concepts useful to other groups. e.g. Enhanced canny edge detection

Gaps:

  • Representing measures as a concept in ITK

Data: 60 datasets. Chest CT scans 1mm resolution. 200mb each. MIDAS? Store as DICOM? Automatically download using CTest.

ITK Algorithms for Analyzing Time-Varying Shape with Application to Longitudinal Heart Modeling

Inputs: Segmentations Outputs: Point sets
Contributions: New ITK module (particle system), filters, classes.

  • Existing code base mostly ITK
  • Port significant portions to ITKv4
  • New ParticleSystem module. New ITK filter process objects.

What support is needed?

  • Logistics of integration and distribution, including data.

Data:

  • 25 longitudinal cardiac DE-MRI (1.25mm in-plane, 2.5mm thick) with segmentations of the left atrium. 2-4 datapoints each (pre ablation, 3mo, 6mo, 1 year)
  • Need IRB to release image data

Gaps:

  • Multivariate stats: Bridge to R for complex statistical analysis without going to file system. Only implement what is needed for within ITK algorithms.