PathML Computational Pathology FAQs

Question 1

Can I use this skill for spatial proteomics or multiplex imaging?

Accepted Answer

Yes. PathML includes specialized workflows for multiparametric imaging data such as CODEX, Vectra, and MERFISH. It facilitates cell segmentation using models like Mesmer and assists in quantifying marker expression for spatial proteomics research.

Question 2

What is the PathML Computational Pathology skill?

Accepted Answer

The PathML Computational Pathology skill is a specialized capability for Claude Code that enables the analysis of whole-slide images (WSI) and multiparametric imaging. It provides Claude with the context and tools needed to build machine learning pipelines for digital pathology, stain normalization, and tissue segmentation.

Question 3

Does this skill include pre-built deep learning models?

Accepted Answer

Absolutely. The skill integrates with popular pathology-specific deep learning architectures like HoVer-Net for nucleus segmentation and classification, as well as HACTNet for hierarchical cell-type classification.

Question 4

Which imaging formats does this Claude Code skill support?

Accepted Answer

This skill supports over 160 slide formats, including common proprietary types like Aperio SVS, Hamamatsu NDPI, Leica SCN, Zeiss ZVI, DICOM, and OME-TIFF, ensuring compatibility with almost any digital pathology hardware.

Question 5

How does PathML improve my research workflow?

Accepted Answer

It streamlines the transition from raw slide images to actionable data by automating complex tasks like tissue detection, Macenko/Vahadane stain normalization, and the construction of spatial graphs for cellular relationship analysis.

PathML Computational Pathology

PathML Computational Pathology

Características Principales

Casos de Uso

Características Principales

Casos de Uso