NucleiSegmentationAndMarkerIDentification

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #typescript #llm #go #golang #android #machine-learning #rust #deep-learning #linux

NucleiSegmentationAndMarkerIDentification

★ 8 Open GitHub ↗

3 different deep learning approaches to segment nuclei and identify associated markers

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# NucleiSegmentationAndMarkerIDentification

These Jupyter notebooks allow to use 5 different deep learning architectures (Mask R-CNN, Cellpose, Stardist, Inception-V3 and U-Net) to segment nuclei. These approaches have been tuned to be efficient in a complex tissue, the mouse intestinal epithelium, with a small dataset.

Marker identification is also performed using an Inception-V3 architecture.

# Video tutorials
Video tutorials are available for: 
[Software installation for Windows](https://www.youtube.com/watch?v=EkFdh9dCQds) 
[Software installation for macOS](https://www.youtube.com/watch?v=y6C9f1jJr5k) 
[Codes downloading and virtual environment creation](https://youtu.be/Q9LOVkQZ_qI) 
[Training U-Net](https://youtu.be/01MHUudZJe4) 
[Running U-Net](https://youtu.be/GzaFf0V3CVU) 
[Training and running Stardist](https://youtu.be/CLNuD7i09Ns) 
[Training and running Cellpose](https://youtu.be/096Dw25bt9s) 
[Training and running Mask R-CNN](https://youtu.be/UUoTdAgACmU) 
[Training and running Inception-V3]()

# Thanks to a Third Party Lib
[Mask R-CNN](https://github.com/matterport/Mask_RCNN) 
[biomagdsb](https://github.com/spreka/biomagdsb)

# Citation
Please cite our paper if you use our method: 
Thierry Pécot, Maria C. Cuitiño, Roger H. Johnson, Cynthia Timmers, Gustavo Leone (2022): [Deep learning tools and modeling to estimate the temporal expression of cell cycle proteins from 2D still images](https://www.biorxiv.org/content/10.1101/2021.03.01.433386v4)

NucleiSegmentationAndMarkerIDentification

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README