pathml

Name: pathml
Availability: InStock
Author: robinbarvaag

Analyze whole-slide images and multiplexed data with Python.

Updated Jan 10, 2026

Search Tags:#machine learning #cell segmentation #whole slide imaging #digital pathology #multiplex imaging #computational pathology

Ready to run

npx skills add https://github.com/robinbarvaag/poynt --skill pathml-robinbarvaag

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pathml
Source: https://github.com/robinbarvaag/poynt/tree/main/.github/skills/pathml
Command: npx skills add https://github.com/robinbarvaag/poynt --skill pathml-robinbarvaag

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.

Core Features & Use Cases

Image Loading & Preprocessing: Handles diverse WSI formats and applies stain normalization, tissue detection, and more.
Cell Segmentation & Graph Construction: Accurately segments cells and builds spatial graphs for neighborhood analysis.
Multiparametric Imaging Analysis: Processes CODEX, Vectra, and MERFISH data for single-cell proteomics and transcriptomics.
Machine Learning Integration: Supports training and inference with pre-built models like HoVer-Net.
Use Case: Analyze spatial interactions between immune cells and tumor cells in multiplex immunofluorescence images by segmenting cells, quantifying marker expression, and building a spatial graph.

Quick Start

Use the pathml skill to load the whole-slide image located at '/path/to/slide.svs'.

Frequently Asked Questions about pathml

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

FAQPage Schema

How do I perform cell segmentation on whole slide images for digital pathology?▼

Cell segmentation on whole slide images is performed by loading the slide and applying advanced preprocessing pipelines to accurately detect and segment nuclei for downstream analysis.

Does this toolkit support loading multiple whole-slide imaging formats?▼

Yes, the toolkit supports loading whole-slide imaging files from over 160 formats, ensuring broad compatibility with diverse digital pathology data sources for preprocessing.

What is the best way to analyze multiplex imaging data like CODEX and MERFISH?▼

Analyzing multiplex imaging data like CODEX and MERFISH involves processing single-cell proteomics and transcriptomics to quantify marker expression and build spatial graphs for neighborhood analysis.

Can I use pre-built machine learning models for nucleus detection and classification?▼

Yes, you can train and run inference with pre-built machine learning models like HoVer-Net to automate nucleus detection and classification tasks in computational pathology.

How does stain normalization work in computational pathology preprocessing pipelines?▼

Stain normalization works by standardizing the color and intensity of tissue staining across different slides, ensuring robust and reproducible analysis in digital pathology research.

When do I need to build spatial graphs from multiplexed imaging data?▼

Spatial graphs are needed to analyze neighborhood interactions, such as mapping spatial relationships between immune cells and tumor cells in multiplexed immunofluorescence images.