Automate computational pathology workflows for whole-slide images and spatial graph analysis.
npx skills add https://github.com/crazymsn/academic-skills --skill pathml-crazymsn
Please help me install this Agent Skill. Skill: pathml Source: https://github.com/crazymsn/academic-skills/tree/main/academic-skills/pathml Command: npx skills add https://github.com/crazymsn/academic-skills --skill pathml-crazymsn
PathML is a comprehensive Python toolkit for computational pathology workflows, designed to facilitate machine learning and image analysis for whole-slide pathology images. The framework provides modular, composable tools for loading diverse slide formats, preprocessing images, constructing spatial graphs, training deep learning models, and analyzing multiparametric imaging data from technologies like CODEX and multiplex immunofluorescence.
Install PathML and run a simple preprocessing pipeline on a sample slide to see results.
High-intent search queries and answers about installing and using this skill.
To load whole-slide images for computational pathology, use a toolkit that supports 160+ formats to access image pyramids and metadata directly. This enables automated preprocessing, stain normalization, and model training across diverse bioimaging files.
Yes, you can build modular preprocessing pipelines for stain normalization and tissue detection. These composable pipelines allow automated quality control and image preparation before constructing spatial graphs or training deep learning models.
Yes, this computational pathology framework supports multiparametric imaging data including CODEX, Vectra, and MERFISH. It processes spatial proteomics and single-cell analysis data to analyze cellular relationships within tissue samples.
To train machine learning models on whole-slide pathology images, use a PyTorch-based workflow with optional distributed processing. The framework supports training models like HoVer-Net and HACTNet on spatial graphs constructed from preprocessed tissue data.
The best way to analyze spatial graphs for cellular relationships is using an end-to-end computational pathology toolkit. It constructs spatial graphs from preprocessed whole-slide images to model tissue architecture and train graph-based ML models.
Yes, you need PyTorch to run machine learning workflows for pathology image analysis. The framework relies on PyTorch-based ML workflows to train deep learning models, with optional distributed processing for handling large whole-slide image datasets.
robotlearning123Load whole-slide images, preprocess, and construct spatial graphs for pathology.
GRIND-Lab-CoreAutomate deployment, execution, and results management of machine learning and spatial data science experiments.
RamanEbrahimiAutomate tissue detection, tile extraction, and preprocessing for whole slide images.
Yezez9Analyze whole-slide images with nucleus segmentation and stain normalization.
