Difference between revisions of "2016 Winter Project Week/Projects/PatchRegistration"

From NAMIC Wiki
Jump to: navigation, search
Line 3: Line 3:
 
Image:PW-MIT2016.png|[[2016_Winter_Project_Week#Projects|Projects List]]
 
Image:PW-MIT2016.png|[[2016_Winter_Project_Week#Projects|Projects List]]
 
Image:WMH_T1.png|Clinical Stroke Image
 
Image:WMH_T1.png|Clinical Stroke Image
 +
Image:MRFRegresult.png|Clinical Stroke Image
 
</gallery>
 
</gallery>
  
Line 27: Line 28:
 
<!-- Add a bulleted list of key points -->
 
<!-- Add a bulleted list of key points -->
 
* We have an implementation of patch-based discrete registration using a standard patch distance metric. We'll start by evaluating this current metric on isotropic images
 
* We have an implementation of patch-based discrete registration using a standard patch distance metric. We'll start by evaluating this current metric on isotropic images
 
+
* We'll develop the infrastracture and evaluate the current metric on isotropic data at large.
 
* We'll develop a new metric for sparse images and test it out.
 
* We'll develop a new metric for sparse images and test it out.
 
|
 
|
 
<!-- Fill this out at the end of Project Week; describe what you did this week and what you plan to do next -->
 
<!-- Fill this out at the end of Project Week; describe what you did this week and what you plan to do next -->
*
+
* We set up registration on a buckner40 dataset with a large number of parameters and launched on a large cluster
 +
* We found a global setting that yields very good results, with volume overlap (DICE) of most subcortical structures in the 80s and 90s.
 +
* Results shown above
 
|}
 
|}

Revision as of 15:08, 8 January 2016

Home < 2016 Winter Project Week < Projects < PatchRegistration

Key Investigators

  • Adrian Dalca (MIT)
  • Andreea Bobu (MIT)
  • Polina Golland (MIT)

Project Description

Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, and analysis, will fail. In part, this is because registration algorithm depend on assumptions of smooth anatomical structures and good quality images, which are not present in these sparse clinical acquisitions. Here, we are investigating a patch-based discrete image registration which allows for more versatile image metrics and does not impose similar assumptions.

Objective Approach and Plan Progress and Next Steps
  • We will investigate a current implementation for patch-based discrete registration on sparse-slice data.
  • We have an implementation of patch-based discrete registration using a standard patch distance metric. We'll start by evaluating this current metric on isotropic images
  • We'll develop the infrastracture and evaluate the current metric on isotropic data at large.
  • We'll develop a new metric for sparse images and test it out.
  • We set up registration on a buckner40 dataset with a large number of parameters and launched on a large cluster
  • We found a global setting that yields very good results, with volume overlap (DICE) of most subcortical structures in the 80s and 90s.
  • Results shown above