Official PyTorch Implementation of paper 'Edge-Based Graph Neural Networks for Cell-Graph Modeling and Prediction'

hierarchical UNI for whole slide image classification

Python 3 Package for optimally sampling big images with texture-aware patchification based on SLIC superpixels. So Sleek !

SurvivMIL: A multimodal, Multiple Instance Learning pipeline for survival outcome of Neuroblastoma Patients

Whole Slide Image Stain Normalisation and Augmentation

This repository is dedicated to the segmentation of histological features in regenerated vascular tissues obtained from tissue-engineered vascular grafts (TEVGs) implanted in sheep.

stain augmentation method based on stainmix up using multiple known stain matrices.

Source code associated to the article "MS-CLAM: Mixed supervision for the classification and localization of tumors in Whole Slide Images" published in Medical Image Analysis.

Self-Supervised Learning in Medicine Review

[MICCAI'24 DEMI Workshop - Best Paper Award] Evaluating Histopathology Foundation Models for Few-shot Tissue Clustering: an Application to LC25000 Augmented Dataset Cleaning

Scripts used for the "Glycophorin C in carotid atherosclerotic plaque reflects intraplaque hemorrhage and pre-procedural neurological symptoms" paper.

On the evaluation of deep learning interpretability methods for medical images under the scope of faithfulness

Feature extraction from GEOJson nuclei and tissue segmentation maps

CLI tool to run specimen-level inference on whole slide images

PyPathomics is an open-source software for gigapixel whole-slide image analysis.

Intel OpenVINO extension for QuPath, a digital pathology platform

Macenko normalisation of big medical slides

SpatialVisVR is a VR platform tailored for advanced visualization and analysis of medical images in immuno-oncology. It allows real-time capture and comparison of mIF and mIHC images via mobile devices. Leveraging deep learning, it matches and displays similar images, supporting up to 100 protein channels.

This repository contains official code for the WACV 2023 paper "HoechstGAN: Virtual Lymphocyte Staining Using Generative Adversarial Networks".