feat(registration): example (poc)

[lscoder]

This PR is a draft (will not be merged) that uses ITK-elastix for the registration of two volumes. https://www.npmjs.com/package/@itk-wasm/elastix

The algorithm seems to run in a webworker by design and it is a mix of GPU and CPU processings (mostly CPU as we can see)

We experimented with various types of registration parameters, and it seems to have decent results so far.

Try here

Run time

The run time seems to be directly related to the number of resolutions, number of iterations and the size of data.

Todo

• See if there are any parameter that can speed up the registration process and/or reduce the amount of memory consumed by the wasm compared to Slicer (eg: Slicer uses 2.5GB and WASM 4GB for the same 300 slices dataset). There are more than 100 parameter map files in Slicer that may help. Go to Slicer/Elastix module > Advanced > Registration Presets and click on "Show database folder"

[netlify]

✅ Deploy Preview for cornerstone-3d-docs ready!

Name	Link
🔨 Latest commit	fe7e58a
🔍 Latest deploy log	https://app.netlify.com/sites/cornerstone-3d-docs/deploys/65440b724720d10008cd5cc7
😎 Deploy Preview	https://deploy-preview-863--cornerstone-3d-docs.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify site configuration.

[sedghi]

see my comments