nucleiseghe

H&E ROI-Level and WSI-Level Nuclei Segmentation with HoVer-Net

https://github.com/cpathology/nucleiseghe

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 4 DOI reference(s) in README
  • Academic publication links
    Links to: sciencedirect.com, springer.com, zenodo.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (8.1%) to scientific vocabulary

Keywords

biomedical-image-analysis computational-pathology deep-learning he-staining hover-net nuclei-segmentation pathology-image pathomics whole-slide-imaging
Last synced: 8 months ago · JSON representation ·

Repository

H&E ROI-Level and WSI-Level Nuclei Segmentation with HoVer-Net

Basic Info
  • Host: GitHub
  • Owner: cpathology
  • License: bsd-3-clause
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 10.4 MB
Statistics
  • Stars: 9
  • Watchers: 1
  • Forks: 3
  • Open Issues: 0
  • Releases: 2
Topics
biomedical-image-analysis computational-pathology deep-learning he-staining hover-net nuclei-segmentation pathology-image pathomics whole-slide-imaging
Created over 3 years ago · Last pushed over 1 year ago
Metadata Files
Readme License Citation

README.md

NucleiSegHE

DOI

H&E ROI-Level and WSI-Level Nuclei Segmentation with HoVer-Net - pretrained model and demo ROIs/WSIs. Demo nuclei overlaying ROI/WSI

Environment Configurations

a. Prepare docker image

  • Build from Dockerfile $ docker build --platform linux/x86_64 -t nucleiseghe:pchen6 .
  • Or pull from Docker Hub $ docker pull pingjunchen/nucleiseghe:pchen6 $ docker tag pingjunchen/nucleiseghe:pchen6 nucleiseghe:pchen6 ### b. Setup docker container
  • Start docker container (specify CODEROOT & DATAROOT) $ docker run -it --rm --user $(id -u):$(id -g) \ -v ${CODE_ROOT}:/App/NucleiSegHE \ -v ${DATA_ROOT}:/Data \ --shm-size=32G --gpus '"device=0"' --cpuset-cpus=0-15 \ --name nucleiseghe_pchen6 nucleiseghe:pchen6
  • For example: $ docker run -it --rm --user $(id -u):$(id -g) \ -v /rsrch1/ip/pchen6/Codes/CHEN/NucleiSegHE:/App/NucleiSegHE \ -v /rsrch1/ip/pchen6/NucleiSegData:/Data \ --shm-size=32G --gpus '"device=0"' --cpuset-cpus=0-15 \ --name nucleiseghe_pchen6 nucleiseghe:pchen6

ROI-Level Nuclei Seg (support png)

Inside the docker container, enter /App/NucleiSegHE ```

Nuclei Segmentation

$ python 01roiseg_nuclei.py --dataset LungNYU

Nuclei Overlay

$ python 02roinuclei_overlay.py --dataset LungNYU ```

WSI-Level Nuclei Seg (support svs/tiff)

Inside the docker container, enter /App/NucleiSegHE ```

Split WSI into smaller blocks (5000 x 5000)

$ python 00wsisplit_blocks.py --dataset CLL

Block-wise WSI nuclei segmentation and merging

$ python 01wsiseg_nuclei.py --dataset CLL

Nuclei overlay to the entire WSI

$ python 02wsinuclei_overlay.py --dataset CLL ```

Acknowledgements

This repo is adapted from following codes - vqdang/hover_net - simongraham/hovernet_inference

Please consider citing the following two papers if this repo was used for nuclei segmentation in your research - Hover-Net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images - PanNuke: an open pan-cancer histology dataset for nuclei instance segmentation and classification

Owner

  • Name: CHEN
  • Login: cpathology
  • Kind: organization
  • Email: pingjunchen@ieee.org
  • Location: United States of America

Computational Heterogeneity & Evolutionary Neoplasia

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - family-names: Chen
    given-names: Pingjun
    orcid: https://orcid.org/0000-0003-0528-1713
title: H&E ROI-Level and WSI-Level Nuclei Segmentation with HoVer-Net
version: V1.0
doi: 10.5281/zenodo.7480809
date-released: 2022-12-25
url: https://github.com/cpathology/NucleiSegHE

GitHub Events

Total
  • Watch event: 2
Last Year
  • Watch event: 2

Dependencies

Dockerfile docker
  • nvidia/cuda 11.6.0-devel-ubuntu20.04 build