Multimodality Image Registration for TBI

• 

  Projects List

• 

  T1 exam1

• 

  T1 exam2

• 

  T1 deformed

Multimodality Image Registration for Traumatic Brain Injury (TBI)

Key Investigators

• Georgia Tech: Yifei Lou and Allen Tannenbaum
• UCLA: Micah Chambers, Andrei Irimia

Objective

• Understanding brain injury using (multimodal) deformable image registration
• Robust registrations inspire of topological changes (enforcing zero flow?)
• The algorithm is based on a viscous fluid model, which can handle larger deformable as compared to the B-spline type of methods
• CUDA-based implementation, which takes 1 min for 256x256x60

Approach, Plan

• Integration into Slicer3 Module
• Learn more about TBI and our data set from Micah (UCLA NA-MIC TBI DBP team member)
• Validate algorithm on additional TBI datasets from UCLA

Progress

• Learn more about TBI and ITK/Slicer
• Demonstrate the efficiency of my algorithm on TBI data
• Its failure in one registration case suggests us dividing 12 modalities into 2 subgroups and co-register within group
• plan to write a paper and integrate my algorithm into ITK/Slicer

References

1 Yifei Lou and Allen Tannenbaum. Multimodal Deformable Image Registration via the Bhattacharyya Distance. Submitted to IEEE Trans. Image Process. 2011

2 Yifei Lou, Xun Jia, Xuejun Gu and Allen Tannenbaum. A GPU-based Implementation of Multimodal Deformable Image Registration Based on Mutual Information or Bhattacharyya Distance. Insight Journal, 2011. [[1]]

Delivery Mechanism

This work will be delivered to the NAMIC Kit as a

1. NITRIC distribution
2. Slicer Module
   1. Built-in: NO
   2. Extension -- commandline: NO
   3. Extension -- loadable: NO