https://github.com/nki-ai/dlup

Dlup are the Deep Learning Utilities for Pathology developed at the Netherlands Cancer Institute
https://github.com/nki-ai/dlup

Last synced: about 2 months ago
JSON representation

Dlup are the Deep Learning Utilities for Pathology developed at the Netherlands Cancer Institute

• Host: GitHub
• URL: https://github.com/nki-ai/dlup
• Owner: NKI-AI
• License: apache-2.0
• Created: 2021-05-22T14:36:39.000Z (almost 5 years ago)
• Default Branch: main
• Last Pushed: 2025-03-07T10:44:06.000Z (about 1 year ago)
• Last Synced: 2025-04-13T11:22:33.033Z (11 months ago)
• Language: Python
• Homepage:
• Size: 2.88 MB
• Stars: 25
• Watchers: 4
• Forks: 7
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.rst
  • License: LICENSE
  • Citation: CITATION.cff

Awesome Lists containing this project

• awesome-pathology - DLUP - Deep learning utilities for pathology. (Software / Machine Learning)

README

          
# Deep Learning Utilities for Pathology

[![pypi](https://img.shields.io/pypi/v/dlup.svg)](https://pypi.python.org/pypi/dlup)

[![Tox](https://github.com/NKI-AI/dlup/actions/workflows/tox.yml/badge.svg)](https://github.com/NKI-AI/dlup/actions/workflows/tox.yml)

[![mypy](https://github.com/NKI-AI/dlup/actions/workflows/mypy.yml/badge.svg)](https://github.com/NKI-AI/dlup/actions/workflows/mypy.yml)

[![Pylint](https://github.com/NKI-AI/dlup/actions/workflows/pylint.yml/badge.svg)](https://github.com/NKI-AI/dlup/actions/workflows/pylint.yml)

[![Black](https://github.com/NKI-AI/dlup/actions/workflows/black.yml/badge.svg)](https://github.com/NKI-AI/dlup/actions/workflows/black.yml)

[![codecov](https://codecov.io/gh/NKI-AI/dlup/branch/main/graph/badge.svg?token=OIJ7F9G7OO)](https://codecov.io/gh/NKI-AI/dlup)

Dlup offers a set of utilities to ease the process of running Deep Learning algorithms on

Whole Slide Images.

## Features

- Read whole-slide images at any arbitrary resolution by seamlessly interpolating between the pyramidal levels

- Supports multiple backends, including [OpenSlide](https://openslide.org/) and [fastslide](https://github.com/NKI-AI/fastslide.git), with the possibility to add custom backends

- Dataset classes to handle whole-slide images in a tile-by-tile manner compatible with pytorch

- Annotation classes which can load GeoJSON, [V7 Darwin](https://www.v7labs.com/), [HALO](https://indicalab.com/halo/) and [ASAP](https://computationalpathologygroup.github.io/ASAP/) formats and read parts of it (e.g. a tile)

- Transforms to handle annotations per tile, resulting, together with the dataset classes a dataset consisting of tiles of whole-slide images with corresponding masks as targets, readily useable with a pytorch dataloader

- Command-line utilities to report on the metadata of WSIs, and convert masks to polygons

Check the [full documentation](https://docs.aiforoncology.nl/dlup) for more details on how to use dlup.

## Quickstart

The package can be installed using `python -m pip install dlup`. Preferably use `uv` and `uv pip install dlup`.

If you wish to install from source, you can run `uv pip install .` You will need the boost package to build from source.

## Used by

- [ahcore](https://github.com/NKI-AI/ahcore.git): a pytorch lightning based-library for computational pathology

## Citing DLUP

If you use DLUP in your research, please use the following BiBTeX entry:

```

@software{dlup,

  author = {Teuwen, J., Romor, L., Pai, A., Schirris, Y., Marcus, E.},

  month = {8},

  title = {{DLUP: Deep Learning Utilities for Pathology}},

  url = {https://github.com/NKI-AI/dlup},

  version = {0.8.0},

  year = {2024}

}

```

or the following plain bibliography:

```

Teuwen, J., Romor, L., Pai, A., Schirris, Y., Marcus E. (2024). DLUP: Deep Learning Utilities for Pathology (Version 0.8.0) [Computer software]. https://github.com/NKI-AI/dlup

```

## Contributors

In alphabetic order:

| [
Ajey Pai Karkala](https://github.com/AjeyPaiK) | [
Eric Marcus](https://github.com/EricMarcus-ai) | [
Jonas Teuwen](https://github.com/jonasteuwen) | [
Leonardo Romor](https://github.com/lromor) | [
Rolf Harkes](https://github.com/rharkes) | [
Yoni Schirris](https://github.com/YoniSchirris) |

| :----------------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------: |