https://github.com/vanvalenlab/tcga-utils
Utilities for handling whole slide images from the The Cancer Genome Atlas (TCGA) Dataset
https://github.com/vanvalenlab/tcga-utils
Last synced: about 1 year ago
JSON representation
Utilities for handling whole slide images from the The Cancer Genome Atlas (TCGA) Dataset
- Host: GitHub
- URL: https://github.com/vanvalenlab/tcga-utils
- Owner: vanvalenlab
- License: other
- Created: 2020-01-11T00:59:18.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2021-12-14T17:35:20.000Z (over 4 years ago)
- Last Synced: 2025-04-20T19:38:05.632Z (over 1 year ago)
- Language: Python
- Size: 20.2 MB
- Stars: 6
- Watchers: 2
- Forks: 2
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# tcga-utils
Utilities for retrieving data from The Cancer Genome Atlas (TCGA) and performing image analysis on whole slide images. This repo is a work in progress and draws heavily from the amazing [python-wsi-preprocessing repo](https://github.com/deroneriksson/python-wsi-preprocessing). This repo contains a Dockerfile to facilitate the creation of a Docker image that has all of the required dependencies installed. Tasks currently supported by this library includes:
* Downloading files from tcga by uuid.
* Opening whole slide images using openslide.
* Converting whole slide images into tiles of a given size and resolution.
* Identify which tiles have images using color filters.
In the near future we will be creating a dataset object to link TCGA images with annotations (gene expression, mutation signature etc) and ease the construction of [data generator objects](https://keras.io/preprocessing/image/) that can be used to train deep learning models.