I already searched the topics here but couldn't figure out clearly what to do so I'm asking here. I have thousands of fiber tracts (the outputs of a tractography algorithm on brain diffusion MRI) that I'd like to cluster them. Each tract is essentially a series of points in 3D Cartesian space. Not all the tracts have the same length and start and end point. How can I extend the DTW to compute the similarity between fiber tracts?

Thank you!


Glad you asked!

There are two ways, DTWi and DTWd. I am 99% sure that for your application, you should do DTWd [a].

You may need to do endpoint invariance [b]. I can advise more if you show me some data. eamonn

[a] http://www.cs.ucr.edu/~eamonn/Multi-Dimensional_DTW_Journal.pdf [b] http://www.cs.unm.edu/~mueen/DTW.pdf

| cite | improve this answer | |
  • $\begingroup$ Thanks for your advice. The data is the coordinates of the fiber tracts saved in a structure variable in MATLAB. How can I share it with you? $\endgroup$ – user3708408 Nov 25 '17 at 16:38

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.