Analyze whole-slide pathology images and multiparametric imaging data for computational pathology workflows.
npx skills add https://github.com/jackspace/ClaudeSkillz --skill pathml
Please help me install this Agent Skill. Skill: pathml Source: https://github.com/jackspace/ClaudeSkillz/tree/main/skills/scientific-pkg-pathml Command: npx skills add https://github.com/jackspace/ClaudeSkillz --skill pathml
PathML provides a comprehensive toolkit to streamline computational pathology workflows: loading a wide range of whole-slide image formats, performing preprocessing (e.g., stain normalization, tissue detection), constructing spatial graphs, training machine learning models, and handling multiparametric imaging data. This reduces manual, repetitive analysis and enables reproducible, scalable pathology research and workflows.
Use Case: Load a repository of H&E slides, apply tissue detection and stain normalization, segment nuclei, build tissue graphs, and train a nucleus classifier at scale, all in a reproducible workflow.
High-intent search queries and answers about installing and using this skill.
PathML loads WSIs from 160+ formats with unified access to pyramids and metadata, then applies modular preprocessing pipelines including stain normalization, tissue detection, and nucleus segmentation. Build reproducible workflows by chaining transforms like StainNormalizationHE and TissueDetectionHE to prepare slides for downstream analysis.
Yes. PathML performs nucleus detection and constructs cellular and tissue graphs for spatial analysis. Segment nuclei across multiple slides, extract spatial relationships, and export results as graphs ready for machine learning or statistical analysis.
PathML handles multiparametric imaging data including CODEX multiplex imaging and spatial proteomics. Load, preprocess, and analyze multiplexed datasets, then export results to AnnData format for integration with downstream computational workflows.
PathML integrates with PyTorch and ONNX to train and deploy ML models on segmented nuclei and spatial features. Build end-to-end pipelines from raw slides through preprocessing, feature extraction, and model training for H&E or multiplex imaging analysis.
PathML uses HDF5 storage and tile-based workflows to manage large-scale datasets. Store preprocessed tiles, features, and spatial graphs efficiently, enabling reproducible analysis across repositories of slides without loading entire images into memory.
PathML provides modular, reusable transforms and pipelines that abstract away complexity. Start with a few lines of code to load a slide, apply preprocessing, and run inference; no prior pathology or deep learning expertise required to begin.
dralkhConvert whole-slide and multiparametric pathology images into normalized tiles, masks, and model-ready datasets.
jasrajtulsiTransforms whole-slide pathology images into structured data via pipelines.
LeonChaoXLoad and preprocess whole-slide pathology images into ML-ready datasets.
crazymsnAutomate computational pathology workflows for whole-slide images and spatial graph analysis.
