Skip to content

Conversation

@vqdang
Copy link
Contributor

@vqdang vqdang commented May 28, 2021

  • Add HoVerNet Architecture and associated post-processing methods
  • Add Nucleus Instance Segmentor to specifically deal with nucleus instance segmentation on WSI levels
  • Add metric function to assess detection quality.
    • F1 detection basing matching point sets.
  • Add function to overlay instance prediction onto canvas or image.
  • Add Tests.

May need another PR to actually improve the doc and better explain the post-processing scheme.

@shaneahmed shaneahmed added the enhancement New feature or request label May 28, 2021
@vqdang vqdang changed the title NEW: Add Feature model segmentation NEW: Add Feature Model Nuclei Instance Segmentation Jul 2, 2021
@shaneahmed shaneahmed self-requested a review November 5, 2021 11:29
Copy link
Contributor

@simongraham simongraham left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nice work. Overall it is looking good - mainly comments to do with docs. Also, please clarify how easy it is to function tiles in addition to wsi ? Ideally we need to be able to allow this with the addition of an argument like we do in patch predictor. Getting the tile level results will be a requirement. If it is incorporated then it needs to be made clear as it seems like it is all geared towards wsi at the moment.

@shaneahmed shaneahmed merged commit fe0b04a into develop Nov 10, 2021
@shaneahmed shaneahmed deleted the feature-model-segmentation branch November 10, 2021 18:28
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

6 participants