histolab

Extract tissue tiles from gigapixel whole slide images for ML datasets.

557|98|Updated Nov 7, 2025
One-click install
npx skills add https://github.com/jimmc414/Kosmos --skill histolab-jimmc414
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: histolab
Source: https://github.com/jimmc414/Kosmos/tree/main/kosmos-claude-scientific-skills/scientific-skills/histolab
Command: npx skills add https://github.com/jimmc414/Kosmos --skill histolab-jimmc414

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the complex and time-consuming process of analyzing whole slide images (WSIs) in digital pathology, enabling efficient computational analysis of histopathology slides.

Core Features & Use Cases

  • Whole Slide Image Processing: Load, inspect, and process gigapixel pathology slides.
  • Tissue Detection & Segmentation: Automatically identify and segment tissue regions.
  • Tile Extraction: Extract informative tiles using random, grid, or score-based strategies.
  • Image Filtering & Preprocessing: Apply various filters for artifact removal and feature enhancement.
  • Visualization: Preview masks, tile locations, and extracted tiles.
  • Use Case: Prepare a dataset of 512x512 pixel tiles from H&E stained whole slide images for training a deep learning model to detect cancer cells, ensuring each tile contains at least 80% tissue.

Quick Start

Use the histolab skill to extract 100 random 512x512 pixel tiles from the whole slide image 'slide.svs', ensuring each tile has at least 80% tissue content.

Frequently Asked Questions about histolab

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

FAQPage Schema
How do I extract tiles from whole slide images for deep learning dataset preparation?

To extract tiles from whole slide images for deep learning dataset preparation, you can use automated tile extraction strategies like random, grid, or score-based sampling to generate specific pixel dimensions from gigapixel pathology slides.

What is computational pathology whole slide image analysis?

Computational pathology whole slide image analysis is the automated process of loading gigapixel slides, detecting tissue regions, and extracting informative tiles to enable efficient digital pathology workflows and dataset preparation.

Can I filter out artifacts and ensure tissue content when extracting histopathology tiles?

Yes, you can filter out artifacts and ensure tissue content by applying image preprocessing filters for artifact removal and using tissue detection segmentation to verify that extracted tiles contain a high percentage of tissue.

What is the best way to process gigapixel digital pathology slides?

The best way to process gigapixel digital pathology slides is using a specialized computational pathology toolkit that handles large WSI formats for automated tissue detection, tile extraction, and visualization.

Do I need specialized libraries to manipulate whole slide imaging files?

Yes, you need specialized libraries for WSI manipulation and image processing to handle the complex gigapixel image formats used in digital pathology whole slide imaging analysis.