If you're doing serious computational pathology work, this is the full toolkit. It handles 160+ slide formats, builds preprocessing pipelines for H&E stain normalization, runs nucleus segmentation models like HoVer-Net, and constructs spatial graphs for tissue analysis. The real power is in the multiparametric imaging support for CODEX and Vectra, where you can segment cells with Mesmer and quantify marker expression. Fair warning, this is GPL-2.0 licensed and heavyweight. If you just need to extract tiles from H&E slides, the docs suggest histolab instead. But for ML model training on pathology data or spatial proteomics analysis, this covers the complete workflow from loading proprietary formats to exporting AnnData for downstream analysis.
npx skills add https://github.com/k-dense-ai/scientific-agent-skills --skill pathml