2012 Summer Project Week:4D Segmentation TBI
- Utah: Bo Wang, Marcel Prastawa, and Guido Gerig
- UCLA: Andrei Irimia, Micah Chambers, Jack Van Horn and Paul M. Vespa
For quantitatively analyzing the recovery and treatment efficacy of MR images with traumatic brain injury (TBI), we introduce a multimodal image segmentation framework for longitudinal TBI images. In the case of longitudinal images with TBI present topological changes over time due to the effect of the impact force and the recovery process, we propose a novel atlas construction scheme that explicitly models the effect of topological changes . The objective of this project week is to contact our collaborators and discuss with them about all the current data set and test the current algorithm by doing more validation.
Our plan for the project week:
- check all the data we have and discuss with our collaborators about the missing modalities and artifacts of some subjects
- discuss with our collaborators about how to visualize the result to help the clinicians.
- do more test using all the data
Summarizing current data
- I've checked and summarized all current TBI data and made a spreadsheet. I've shared the spreadsheet with Andrei.
Attending breakout session
- Bo and Andrei attended the breakout session of Registration of Difficult Images.
- After talking to Andrei, we thought we should visualize the segmentation by overlaying the deformation field or cortical thickness.
- Bo Wang, Marcel Prastawa, Suyash P. Awate, Andrei Irimia, Micah C. Chambers, Paul M. Vespa, John D. Van Horn, and Guido Gerig, Segmentation of Serial MRI of TBI patients using Personalized Atlas Construction and Topological Change Estimation, IEEE International Symposium on Biomedical Imaging (ISBI) 2012.