PathML objective is to lower the barrier to entry to digital pathology.
Examples:
- Load over 160+ different types of pathology images using PathML
- H&E Stain Deconvolution and Color Normalization
- Brightfield imaging pipeline: load an image, preprocess it on a local cluster, and get it read for machine learning analyses in PyTorch
- Multiparametric Imaging: Quickstart & single-cell quantification
- Multiparametric Imaging: CODEX & nuclei quantization
- Train HoVer-Net model to perform nucleus detection and classification, using data from PanNuke dataset
- Gallery of PathML preprocessing and transformations
More information at: https://github.com/Dana-Farber-AIOS/pathml
in a hurry? docker pull pathml/pathml && docker run -it -p 8888:8888 pathml/pathml