cbm24sasnil

Reimplementation of CBM'24 paper Unsupervised Domain Adaptation for Histopathology Image Segmentation with Incomplete Labels

https://github.com/itomxy/cbm24sasnil

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
    Found 2 DOI reference(s) in README
  • Academic publication links
    Links to: sciencedirect.com
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (9.0%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Reimplementation of CBM'24 paper Unsupervised Domain Adaptation for Histopathology Image Segmentation with Incomplete Labels

Basic Info
  • Host: GitHub
  • Owner: iTomxy
  • License: mit
  • Language: Python
  • Default Branch: main
  • Size: 146 KB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed 8 months ago
Metadata Files
Readme Citation

README.md

This repository contains an unofficial, partial implementation of paper:

Huihui Zhou, Yan Wang, Benyan Zhang, Chunhua Zhou, Maxim S. Vonsky, Lubov B. Mitrofanova, Duowu Zou, and Qingli Li. 2024. Unsupervised domain adaptation for histopathology image segmentation with incomplete labels. Comput. Biol. Med. 171, C (Mar 2024). https://doi.org/10.1016/j.compbiomed.2024.108226

I only implement its incomplete label correction stage as a baseline of incomplete label segmentation task. Also, I have NOT tested this implementation on its original dataset.

Backbone

The original paper uses DAFormer as its backbone, which is develop upon MMSegmentation. But it is hard to hack. Thus I instead use UNet from MONAI as backbone.

Data

See iTomxy/data/totalsegmentator.

Dependencies

Train & Test

shell bash run.sh

Citation

If you find this repository helpful, please consider citing it as follows:

@software{Liang_Reimplementation_of_SASN-IL, author = {Liang, Tianyou}, title = {Reimplementation of SASN-IL}, url = {https://github.com/iTomxy/cbm24sasnil}, version = {2024.8.17} }

You can also export this BibTeX or APA format citation string via the Cite this repository at the right-side panel of this GitHub repository page.

You may also want to cite the original paper, see here.

Owner

  • Name: iTom
  • Login: iTomxy
  • Kind: user
  • Company: The Chinese University of Hong Kong (Shenzhen)

tom.tyliang@gmail.com hackeritom@163.com

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Liang"
  given-names: "Tianyou"
  orcid: "https://orcid.org/0000-0002-2213-3029"
title: "Reimplementation of SASN-IL"
version: 2024.8.17
date-released: 2024-8-187
url: "https://github.com/iTomxy/cbm24sasnil"

GitHub Events

Total
  • Push event: 7
Last Year
  • Push event: 7

Dependencies

requirements.txt pypi
  • matplotlib *
  • medpy >=0.5.2
  • monai *
  • nibabel *
  • opencv-python *
  • scikit-image *
  • scipy *
  • tensorboard *
  • torch ==1.13.1
  • torchvision ==0.14.1