pathml

Load and preprocess whole-slide images for computational pathology workflows.

Updated Mar 10, 2026
One-click install
npx skills add https://github.com/felixboehm/biochem-allergy --skill pathml-felixboehm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pathml
Source: https://github.com/felixboehm/biochem-allergy/tree/main/.claude/skills/pathml
Command: npx skills add https://github.com/felixboehm/biochem-allergy --skill pathml-felixboehm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines complex computational pathology workflows, enabling advanced analysis of whole-slide images and multiplexed data without requiring deep expertise in each sub-domain.

Core Features & Use Cases

  • WSI Loading & Preprocessing: Handles 160+ slide formats, stain normalization, and tissue/nucleus segmentation.
  • Spatial Graph Construction: Builds cell and tissue graphs for spatial analysis.
  • ML Model Training & Inference: Integrates with PyTorch for training and ONNX for deployment.
  • Multiparametric Imaging: Supports CODEX, Vectra, and MERFISH data analysis.
  • Use Case: Analyze multiplex immunofluorescence images to segment cells, quantify marker expression, annotate cell types, and build spatial graphs to study tumor microenvironment interactions.

Quick Start

Use the pathml skill to load a whole-slide image and perform stain normalization.

Frequently Asked Questions about pathml

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I load and preprocess whole-slide images for computational pathology analysis?

You can load whole-slide images across 160+ formats and apply preprocessing techniques like stain normalization and tissue segmentation to prepare slides for downstream machine learning analysis.

What is spatial graph construction in multiplex imaging data analysis?

Spatial graph construction in multiplex imaging builds cell and tissue graphs from segmented images, enabling spatial analysis of interactions within the tumor microenvironment using data from platforms like CODEX and Vectra.

Can I use PyTorch and ONNX for machine learning model training and deployment in pathology workflows?

Yes, pathology workflows support PyTorch integration for machine learning model training and ONNX for model deployment, streamlining the transition from nucleus segmentation to inference.

How do I segment cells and quantify marker expression in multiplex immunofluorescence images?

Cell segmentation and marker expression quantification in multiplex immunofluorescence images are performed by analyzing CODEX, Vectra, and MERFISH data to annotate cell types and study tumor microenvironment interactions.

Do I need deep expertise in computational pathology to analyze whole-slide images and multiplexed data?

No deep expertise in each sub-domain is required, as comprehensive pathology toolkits streamline complex workflows for whole-slide images and multiplexed data, handling loading, preprocessing, and segmentation automatically.