https://github.com/andreped/pathology-representation-simulation

🚀 Create your own simulation of t-SNE on histopathology images!
https://github.com/andreped/pathology-representation-simulation

clustering dimensionality-reduction histopathology pathology representation simulation t-sne tensorboard tensorboard-projector training wsi

Last synced: about 2 months ago
JSON representation

🚀 Create your own simulation of t-SNE on histopathology images!

• Host: GitHub
• URL: https://github.com/andreped/pathology-representation-simulation
• Owner: andreped
• License: mit
• Created: 2024-11-03T19:13:21.000Z (3 months ago)
• Default Branch: main
• Last Pushed: 2024-11-05T07:41:03.000Z (3 months ago)
• Last Synced: 2024-12-19T22:09:52.702Z (about 2 months ago)
• Topics: clustering, dimensionality-reduction, histopathology, pathology, representation, simulation, t-sne, tensorboard, tensorboard-projector, training, wsi
• Language: Jupyter Notebook
• Homepage:
• Size: 17.3 MB
• Stars: 3
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Pathology t-SNE simulation

[![license](https://img.shields.io/github/license/DAVFoundation/captain-n3m0.svg?style=flat-square)](https://github.com/andreped/pathology-representation-simulation/blob/main/LICENSE.md)



This repository contains a simple demonstration of how t-SNE can be used to 

represents different tissue types in histopathological images.



## Stack

For this demonstration I used Jupyter Notebook to make it easy for others to reproduce.

I also used the following Python packages:

* [TensorBoard](https://pypi.org/project/tensorboard/) (with [Embedding Projector](https://www.tensorflow.org/tensorboard/tensorboard_projector_plugin) plugin)

* [medmnist](https://pypi.org/project/medmnist/) (to access the [MedMNIST](https://medmnist.com) histopathology image dataset)

* [Pillow](https://pypi.org/project/pillow/)

* [NumPy](https://pypi.org/project/numpy/)

## Getting started

To recreate a similar video to the one above, you can simply run the Jupyter Notebook (see under `assets/`).  

Note that you may need to run the last cell a few times before the TensorBoard dashboard shows.  

When it opens, enable **Spherizie Data** by clicking the checkbox on the left-hand sidebar.  

Then click the **T-SNE** option underneath. This should start the simulation immediantly.  

Then just play around with hyperparameters to get a simulation you are pleased with.

For the actual recording, I used screen recording on my macOS 14.6 using `CMD + SHIFT + 5`

and selecting a window, but use whichever tool you prefer :]

To convert recording to GIF, use any video converter like [ezgif](https://ezgif.com/video-to-gif) or similar.

## Citation

If you use this illustration in a presentation or publication, please cite it using the repository URL.

## Acknowledgements

Implementations were based on the code provided in [this blog post](https://learnopencv.com/t-sne-t-distributed-stochastic-neighbor-embedding-explained/).

## License

This project has MIT license.