Skip to content
  • Search
Skins
  • Light
  • Cerulean
  • Cosmo
  • Flatly
  • Journal
  • Litera
  • Lumen
  • Lux
  • Materia
  • Minty
  • Morph
  • Pulse
  • Sandstone
  • Simplex
  • Sketchy
  • Spacelab
  • United
  • Yeti
  • Zephyr
  • Dark
  • Cyborg
  • Darkly
  • Quartz
  • Slate
  • Solar
  • Superhero
  • Vapor

  • Default (No Skin)
  • No Skin
Collapse

ZMT zurich med tech

  1. Home
  2. Sim4Life
  3. Anatomical Models
  4. New Notebook Tutorials for Personalized Simulations using our Body Segmentation AI

New Notebook Tutorials for Personalized Simulations using our Body Segmentation AI

Scheduled Pinned Locked Moved Anatomical Models
1 Posts 1 Posters 6 Views 1 Watching
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • brynB Online
    brynB Online
    bryn
    ZMT
    wrote last edited by
    #1

    I would like to highlight our new jupyter notebooks released in Sim4Life 9.0 (18820) demonstrating how to setup simulations for personalized modeling, starting from medical image data (MRI or CT). You can find them under Help -> Examples, tutorials H, J and K.

    40ce376e-f66a-4cef-9f92-47a5f23f41be-image.png

    These new tutorials show how to

    • import medical images
    • run automatic segmentation of the trunc
    • extract surface models from the labelfields
    • assign material tags to simplify automatic assignment of material properties in the simulations
    • extracting anatomical landmarks on the skin for placing electrodes
    • setting up a simulation and running it

    We would love to get constructive feedback and suggestions. In our experiments the segmentation seems quite robust, but errors may occur (this is not a clinical tool). We try to fix these errors in the post-processing, but there are most certainly cases where the post-processing may do something unintended (like add skin at the border of the field of view, where there should be none). If you have a need for making this robust for your data, contact us at virtualpopulation@itis.swiss so we can discuss.

    1 Reply Last reply
    0
    Reply
    • Reply as topic
    Log in to reply
    • Oldest to Newest
    • Newest to Oldest
    • Most Votes


    • Login

    • Don't have an account? Register

    • Login or register to search.
    • First post
      Last post
    0
    • Search