Project-MONAI / Project-MONAI/model-zoo
oir_flatmount_segmentation - Hartnett lab model submission
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 339
- Forks
- 106
- PR merge metrics
- No merged PRs in 30d
Description
Model name: oir_flatmount_segmentation
Task: Segmentation of total retina (TR), intravitreal neovascularization (IVNV), and avascular area (AVA) in mouse and rat OIR retinal flatmount images.
Repository URL: https://github.com/hartnettlabteam/oir_flatmount_segmentation
We are submitting a MONAI bundle for automated OIR flatmount segmentation (TR, IVNV, AVA) using an Attention U-Net/ConvNeXt-Tiny pipeline with 5-fold ensemble inference. Large model weights are hosted as GitHub release assets and referenced via large_files.yml.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the submitted repository at https://github.com/hartnettlabteam/oir_flatmount_segmentation and its large_files.yml reference. Check how the MONAI bundle represents the Attention U-Net/ConvNeXt-Tiny pipeline, five-fold ensemble inference, and release-hosted weights. Done means the model submission is complete and usable for TR, IVNV, and AVA segmentation on the stated mouse and rat images.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 52/100