skills.rest
jimmc414
jimmc414COMMUNITY
Explore all skills by this author →
𝕏@JimMcM4GitHub

pathml

Processes computational pathology workflows with WSI loading, preprocessing, ML models, and spatial graphs.

557|98|Updated Nov 7, 2025
Search Tags:#machine learning#pathology#histology#whole slide imaging#multiplex imaging#computational pathology
One-click install
npx skills add https://github.com/jimmc414/Kosmos --skill pathml-jimmc414
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pathml
Source: https://github.com/jimmc414/Kosmos/tree/main/kosmos-claude-scientific-skills/scientific-skills/pathml
Command: npx skills add https://github.com/jimmc414/Kosmos --skill pathml-jimmc414

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a comprehensive toolkit for computational pathology, enabling advanced analysis of whole-slide images and multiplexed data.

Core Features & Use Cases

  • Image Loading: Supports 160+ WSI formats (Aperio, NDPI, DICOM, OME-TIFF).
  • Preprocessing: Stain normalization, tissue/nucleus detection, artifact labeling.
  • Machine Learning: Pre-built HoVer-Net and HACTNet models for nucleus segmentation and classification.
  • Graph Construction: Build spatial graphs for cell-cell interaction analysis.
  • Multiparametric Imaging: Specialized workflows for CODEX, Vectra, and MERFISH data.
  • Use Case: Analyze tumor microenvironments by loading a whole-slide image, segmenting nuclei, quantifying marker expression, and building a spatial graph to study immune cell interactions.

Quick Start

Use the pathml skill to load the whole-slide image at 'path/to/slide.svs' and generate tiles of size 256x256.

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?▼

Load 160+ WSI formats like Aperio, NDPI, and DICOM, then apply stain normalization and tissue detection. Generate tiles of specific sizes to prepare whole-slide images for downstream machine learning analysis.

What machine learning models are available for nucleus segmentation in histopathology slides?▼

Pre-built HoVer-Net and HACTNet models are integrated for nucleus segmentation and classification. Apply these models to whole-slide histopathology images to detect, segment, and classify nuclei.

Can I analyze multiplex imaging data like CODEX and MERFISH spatial omics?▼

Specialized workflows support multiparametric imaging data including CODEX, Vectra, and MERFISH. Load spatial omics datasets to quantify marker expression and analyze cell-cell interactions.

How do I build spatial graphs for cell-cell interaction analysis in tumor microenvironments?▼

Construct spatial graphs after segmenting nuclei and quantifying marker expression. Build these graphs to analyze cell-cell interactions and study immune cell dynamics within tumor microenvironments.

Does this computational pathology toolkit require specific format dependencies for OME-TIFF files?▼

No dependencies are required. The toolkit natively supports loading OME-TIFF whole-slide images alongside 160 other formats, enabling direct preprocessing without external library installations.

What is the best way to normalize staining artifacts in histology slides?▼

Apply stain normalization and artifact labeling during the preprocessing phase. Normalize histology slides to correct staining variations and label artifacts before running tissue and nucleus detection.

Related Skills

Explore More Data & Analytics Skills→
LogauaEngstromLogauaEngstrom
18

histolab

Automate preprocessing and analysis of whole-slide images for digital pathology workflows.

Community
Advanced
jackspacejackspace
16

histolab

Extract informative tiles and detect tissue regions from whole slide images.

Community
Advanced
shushuznshushuzn
4

pathml

Convert whole-slide pathology images into ML-ready datasets with HDF5 storage.

Community
Advanced
jaechang-hitsjaechang-hits
298

pathml

Process whole-slide images with tiling, stain normalization, and nuclear segmentation.

Community
Advanced