histolab

Extract informative tiles from whole slide images using tissue detection and mask generation.

Updated May 24, 2026
One-click install
npx skills add https://github.com/Estrella-231/Mathematical_modeling_tongmeng --skill histolab-estrella-231
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: histolab
Source: https://github.com/Estrella-231/Mathematical_modeling_tongmeng/tree/main/.agents/skills/histolab
Command: npx skills add https://github.com/Estrella-231/Mathematical_modeling_tongmeng --skill histolab-estrella-231

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Whole slide images are extremely large and hard to analyze directly, so researchers need reliable automation to detect tissue, extract informative regions, and prepare consistent tile datasets.

Core Features & Use Cases

  • WSI tile extraction & dataset preparation: Automatically extracts tiles from gigapixel slides using random sampling, grid coverage, or score-based selection.
  • Tissue detection & masking: Builds tissue masks to exclude background/artifacts and to define where tiles are extracted.
  • Preprocessing pipeline tooling: Supports filter composition (color transforms, thresholding, morphological cleanup) to improve mask quality and tile usability.

Use cases: Create balanced deep-learning training sets from H&E slides, speed up WSI preprocessing before model training, and curate high-quality tiles focused on nuclei-rich regions for downstream analysis.

Quick Start

Use the histolab skill to extract 512x512 tissue tiles from a whole slide image named slide.svs at pyramid level 0 into an output folder.

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 datasets?

Whole slide image tile extraction involves applying tissue detection to generate masks, then performing random sampling, systematic grid coverage, or score-based selection to output configurable tiles for deep learning datasets.

What is tissue masking in H&E whole slide image preprocessing?

Tissue masking in H&E whole slide image preprocessing builds masks to exclude background and artifacts, defining exact extraction boundaries so only informative tissue regions are selected for downstream analysis.

Can I configure tile size and extraction level for whole slide image preprocessing?

Yes, whole slide image preprocessing supports configurable tile size and extraction level requirements, allowing deterministic, parameterized extraction across specific slide pyramid levels and custom tile dimensions.

Does whole slide image tile extraction support color transforms and morphological cleanup filters?

Whole slide image tile extraction supports composable image preprocessing filters, including color transforms, thresholding, and morphological cleanup, to improve tissue mask quality and final tile usability.

What is the best way to handle background artifacts when extracting tissue tiles from WSI?

Handling background artifacts when extracting tissue tiles from WSI requires building tissue masks and applying composable preprocessing filters like thresholding and morphological cleanup to isolate informative tissue regions.