histolab

Process whole slide images by detecting tissue regions and extracting tiles.

Updated Dec 17, 2025

Search Tags:#image processing #digital pathology #computational pathology #tissue segmentation #whole slide image

Ready to run

npx skills add https://github.com/robotlearning123/claude-scientific-skills --skill histolab-robotlearning123

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: histolab
Source: https://github.com/robotlearning123/claude-scientific-skills/tree/main/scientific-skills/histolab
Command: npx skills add https://github.com/robotlearning123/claude-scientific-skills --skill histolab-robotlearning123

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openslide, numpy, scikit-image, Pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies the processing of whole slide images (WSIs) in digital pathology, enabling efficient tissue detection, tile extraction, and preprocessing for deep learning pipelines.

Core Features & Use Cases

Whole Slide Image Management: Load, inspect, and work with WSI files in various formats.
Tissue Detection and Masks: Automatically identify tissue regions and filter background/artifacts.
Tile Extraction: Extract smaller regions from large WSI using different strategies.
Filters and Preprocessing: Apply image processing filters for tissue detection, quality control, and preprocessing.
Visualization: Visualize slides, masks, tile locations, and extraction quality.
Use Case: For instance, a researcher might use this Skill to automatically extract tiles from a whole slide image, segment the tissue, and prepare the data for a deep learning model training.

Quick Start

Use the histolab skill to extract tiles from the 'whole_slide_image.svs' file and save them as 'output_tiles.png'.

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 digital pathology?▼

To extract tiles from whole slide images, you can automate the process by detecting tissue regions and applying specific extraction strategies to isolate smaller regions from large WSI files. This workflow prepares the data for deep learning model training.

What is the best way to detect tissue regions and filter background in WSI files?▼

Detecting tissue regions in WSI files is best handled by applying automated tissue detection algorithms that generate masks, effectively filtering out background and artifacts. This isolates the relevant tissue for accurate computational pathology analysis.

Can I use Python libraries like OpenSlide and scikit-image for computational pathology workflows?▼

Yes, you can use Python libraries like OpenSlide and scikit-image for computational pathology workflows, as they provide the necessary foundation for loading various WSI formats and applying image processing filters for tissue segmentation and quality control.

How do I prepare whole slide image datasets for deep learning pipelines?▼

Preparing whole slide image datasets for deep learning pipelines involves loading WSI files, automatically detecting tissue regions, extracting smaller tiles, and applying image preprocessing filters. This process ensures the data is clean and properly formatted for model ingestion.

Does whole slide image processing support visualization of tissue masks and tile locations?▼

Yes, whole slide image processing supports visualization of tissue masks and tile locations. You can visualize slides, generated masks, and extraction quality to verify that the tissue segmentation and tile extraction meet your dataset preparation standards.

What image processing filters are needed for tissue segmentation in digital pathology?▼

Image processing filters needed for tissue segmentation in digital pathology are used to automatically identify tissue regions, perform quality control, and preprocess the whole slide images. These filters ensure accurate tissue detection and artifact removal prior to analysis.