Difference between revisions of "Projects:RegistrationDocumentation:ParameterTesting"
From NAMIC Wiki
(Created page with '=== ISMRM abstract 2010 === *'''Title:''' MR-protocol Tailored Medical Image Registration *'''Objective:''' Determine optimized sets of parameters for successful automated regis…') |
|||
| Line 2: | Line 2: | ||
*'''Title:''' MR-protocol Tailored Medical Image Registration | *'''Title:''' MR-protocol Tailored Medical Image Registration | ||
| − | *'''Objective:''' Determine optimized sets of parameters for successful automated registration of MR-MR images. DOF, cost function, initialization and optimization strategy will differ because of the differences in image contrast and/or content. This work will present approaches and solutions for successful registration for a large set of combinations of MRI pairings. | + | *'''Objective:''' Determine optimized sets of parameters for successful automated registration of MR-MR images within the 3DSlicer software. DOF, cost function, initialization and optimization strategy will differ because of the differences in image contrast and/or content. This work will present approaches and solutions for successful registration for a large set of combinations of MRI pairings. This is part of a concerted effort to build a Registration Case Library available to the medical imaging research community. |
*'''Method:''' | *'''Method:''' | ||
**1- we choose 3-4 subjects/exams with 3-4 different contrast pairings: T1, T2, PD, FLAIR: ~12-16 images | **1- we choose 3-4 subjects/exams with 3-4 different contrast pairings: T1, T2, PD, FLAIR: ~12-16 images | ||
| Line 11: | Line 11: | ||
**6-extension 1: add different voxel sizes, i.e. emulate 1,3,5mm slice thickness | **6-extension 1: add different voxel sizes, i.e. emulate 1,3,5mm slice thickness | ||
**7- extension 2: add initial misalignment as parameter to the test series | **7- extension 2: add initial misalignment as parameter to the test series | ||
| − | *Options: The expert landmark selection as rate-limiting step we could bypass by doing this as a self-validation where we start from a registration we consider optimal and then apply pre-determined misalignment. We then do not need fiducial pairs to evaluate. | + | *Options: The expert landmark selection as rate-limiting step we could bypass by doing this as a self-validation where we start from a registration we consider optimal and then apply pre-determined misalignment. We then do not need fiducial pairs to evaluate but can derive RMS metrics from the result Xform directly. We will have to justify/scrutinize how we chose our gold-standard. A true gold-standard would exist only for prospectively aligned image sets, such as a dual echo PD/T2. |
*This is somewhat pedestrian but in line with our advertisement objective, i.e. we can mention that these and other tests will be part of the 3Dslicer registration use-case library. | *This is somewhat pedestrian but in line with our advertisement objective, i.e. we can mention that these and other tests will be part of the 3Dslicer registration use-case library. | ||
Revision as of 16:39, 27 October 2009
Home < Projects:RegistrationDocumentation:ParameterTestingISMRM abstract 2010
- Title: MR-protocol Tailored Medical Image Registration
- Objective: Determine optimized sets of parameters for successful automated registration of MR-MR images within the 3DSlicer software. DOF, cost function, initialization and optimization strategy will differ because of the differences in image contrast and/or content. This work will present approaches and solutions for successful registration for a large set of combinations of MRI pairings. This is part of a concerted effort to build a Registration Case Library available to the medical imaging research community.
- Method:
- 1- we choose 3-4 subjects/exams with 3-4 different contrast pairings: T1, T2, PD, FLAIR: ~12-16 images
- 2- we have an expert reader determine ~ 3-5 anatomical landmarks on each unregistered image
- 3- we register all combinations and run a sensitivity analysis for the most critical parameters: 6 vs. 12 DOF, cost function, % sampling
- 4- outcome metric is RMS error of fiducial alignment
- 5- we report the best performing parameter set for each MR-MR combination
- 6-extension 1: add different voxel sizes, i.e. emulate 1,3,5mm slice thickness
- 7- extension 2: add initial misalignment as parameter to the test series
- Options: The expert landmark selection as rate-limiting step we could bypass by doing this as a self-validation where we start from a registration we consider optimal and then apply pre-determined misalignment. We then do not need fiducial pairs to evaluate but can derive RMS metrics from the result Xform directly. We will have to justify/scrutinize how we chose our gold-standard. A true gold-standard would exist only for prospectively aligned image sets, such as a dual echo PD/T2.
- This is somewhat pedestrian but in line with our advertisement objective, i.e. we can mention that these and other tests will be part of the 3Dslicer registration use-case library.
