2014 Summer Project Week:LongitudinalSeg
- Iowa: Regina Kim
- Iowa: Hans Johnson
- Utah: James Fishbaugh
- Utah: Guido Gerig
Longitudinal imaging studies involve tracking changes in individuals by repeated image acquisition over time. The goal of these studies is to quantify biological shape variability within and across individuals, and also to distinguish between normal and disease populations. However, data variability is influenced by outside sources such as image acquisition, image calibration, human expert judgement, and limited robustness of segmentation and registration algorithms.
- Deploy a shape analysis tool for large-scale multi center data processing
- Apply & validate the tool on longitudinal data sample (BRAINSCut Segmentation)
- extension of tests to MABMIS results
- extension of tests to MALF (ANTs) results
- Visual comparison of shape analysis.
- Tool has been migrated into University of Iowa cite.
- Shape changes are detected using both MALF and BRAINSCut segmentation
- One subjects of five time points data in the course of 8 years period.
- Putamen and caudate tested
- About 10 hours for 50 iterations.
- A new tool experience: Multi-atlas Slicer extension module from JHU
- Future Work:
- Shape smoothing parameter determination
- Investigation of Pros & Cons using different segmentation tool