shapeworks-users

Text archives Help


Re: [shapeworks-users] Using Shapeworks


Chronological Thread 
  • From: Jainta Paul <1605022@ugrad.cse.buet.ac.bd>
  • To: Shireen Elhabian <shireen@sci.utah.edu>
  • Cc: shapeworks-users@sci.utah.edu
  • Subject: Re: [shapeworks-users] Using Shapeworks
  • Date: Fri, 25 Jun 2021 22:07:49 +0600
  • Ironport-sdr: 29Rp64BTfTAnSH+gPGC+EyPOx/gbPmsqBkPsAYtUx7zohJeSheA9bjQxPAk43qqvSq+yJxqFlc SKItuiK//6BXvwQU7BP1o9kqC80RVwo8IYuBbl1dc+wgtKS96lJVutTI+Rvb65joLy2zUN1EYL TdVB4rvNPtgiVUIbsAODNjlj0rTsMlJ+ECaBOoTGqVsnlkIi5Fu2EI36YLG1jGb/9xWCHh36SU jw9getErXCsBHTIrtyjWHppJpUVwScQ1iZ7HHmCbUu1v55LxbyC93jCaxxMdZX6klg3t2QKvvY Hjg=

Thanks for the information. 

On Fri, 25 Jun 2021, 10:06 pm Shireen Elhabian, <shireen@sci.utah.edu> wrote:
Dear Jainta,

I see now why you were looking at DeepSSM papers. Please note that DeepSSM needs SSM for training purposes. So the first step to build an SSM is to segment the anatomy of interest from CT/MRI images and export these segmentations as either binary volumes or surface meshes. 

The next step is to quality control these segmentations to make sure that are no non-anatomical artifacts (e.g., protrusions, holes, bone islands … etc) exist that should not be captured by the SSM. A smooth water-tight surface mesh is the best input for shape modeling. We updated the documentation to provide some illustrations. This will be included in the 6.1 release, for now, you can access these examples here https://github.com/SCIInstitute/ShapeWorks/blob/misc_61/docs/getting-started/shapes.md 

Below are some free software packages that can help you with manual and/or semi-automated image segmentations.



Regards
Shireen


------------------------------------------
Shireen Elhabian, M.Sc., Ph.D.
Research Assistant Professor, School of Computing
Research Computer Scientist, Scientific Computing and Imaging Institute
University of Utah
WEB 2815
72 Central Campus Drive, Salt Lake City, UT, 84112
Phone (801) 587-3206
Fax (801) 585-6513
Home Page: http://www.sci.utah.edu/~shireen

On Jun 24, 2021, at 7:01 PM, Jainta Paul <1605022@ugrad.cse.buet.ac.bd> wrote:

Dear Professor Shireen,
My thesis goal is to make a system that can create an SSM from CT/MRI Dicom images and predict bone fracture probability.
Can you give me some guidelines about how I can approach and use Shapeworks?  

On Fri, Jun 25, 2021 at 5:24 AM Shireen Elhabian <shireen@sci.utah.edu> wrote:
Dear Jainta,

If you are interested in the algorithmic side of ShapeWorks, I am attaching the book chapter referred to http://sciinstitute.github.io/ShapeWorks/users/citation.html 

Could you elaborate more on your thesis focus? What do you want to use ShapeWorks for?

Regards
Shireen


------------------------------------------
Shireen Elhabian, M.Sc., Ph.D.
Research Assistant Professor, School of Computing
Research Computer Scientist, Scientific Computing and Imaging Institute
University of Utah
WEB 2815
72 Central Campus Drive, Salt Lake City, UT, 84112
Phone (801) 587-3206
Fax (801) 585-6513
Home Page: http://www.sci.utah.edu/~shireen

On Jun 23, 2021, at 11:52 AM, Jainta Paul <1605022@ugrad.cse.buet.ac.bd> wrote:

Dear users,
For my undergrad thesis, I am required to use Shapeworks. I am new to this field and as a result, it's becoming hard for me to find out where to start. I have already gone through the documentation several times but could not find any clue regarding the algorithms Shapeworks is using. I have also read the papers titled  "Uncertain-DeepSSM: From Images to Probabilistic Shape Models" and "DeepSSM: A Deep Learning Framework for Statistical Shape Modeling from Raw Images"  but could not understand the algorithms properly. It would be really nice if you can give me some guidelines.
Thank you.





Archive powered by MHonArc 2.6.18.

Top of page