histolab

Whole-slide image tile extraction applies tissue masks and multiple tiling strategies to isolate tissue regions, producing consistent tiles for deep learning dataset preparation across SVS, TIFF, and NDPI formats.

Whole-slide image dataset preparation automates slide management, metadata extraction, and tile extraction to generate consistent tissue tiles, producing reproducible deep learning training datasets for digital pathology workflows.

Yes, whole-slide image processing supports SVS, TIFF, and NDPI formats, automating slide management and metadata extraction to enable tissue detection and tiling for pathology research pipelines.

Generating tissue masks and visualizing quality control applies automated tissue detection to whole-slide images, producing masks and reports that ensure reproducibility and support quality control in pathology workflows.

Yes, tile extraction from whole-slide images supports multiple tiling strategies, allowing you to configure a tiler and apply different extraction methods to generate diverse tile datasets for deep learning pipelines.

YAML frontmatter with name and description is required for whole-slide image processing tasks to support discovery and execution, ensuring proper task identification and enabling optional resources like scripts or references.