/ALL-IN

The code for ALL-IN: A Local GLobal Graph-based DIstillatioN Model for Representation Learning of Gigapixel Histopathology Images With Application In Cancer Risk Assessment

MIT LicenseMIT

ALL-IN

This repository contains the Pytorch implementation and the used graph embeddings in "ALL-IN: A Local GLobal Graph-based DIstillatioN Model for Representation Learning of Gigapixel Histopathology Images With Application In Cancer Risk Assessment" paper, accepted at MICCAI 2023.

Note

  • Both the embeddings and training/testing codes will be available in this repository.
  • We are currently in the process of code and data cleaning. Stay tuned!

TODOs

Please follow this GitHub for more updates.

  • Documentation on training and evaluating the models.
  • Releasing the code post-training analyses including kaplan-meier plots and logrank tests
  • Cleaning the data to be ready for the public use.
  • Publishing the pytorch implementation for all 3 distillation strategies presented in paper.