What slide formats does the PathML skill support?

PathML supports over 160 proprietary formats, including common ones like Aperio SVS, Hamamatsu NDPI, Leica SCN, Zeiss ZVI, DICOM, and OME-TIFF.

Does this skill support deep learning for pathology?

Absolutely. PathML integrates with PyTorch and provides pre-built architectures like HoVer-Net for simultaneous nucleus segmentation and classification.

How does PathML handle very large pathology datasets?

It utilizes HDF5 storage structures to efficiently manage tiles, masks, and metadata, making it suitable for large-scale machine learning workflows.

Can PathML be used for multiplex immunofluorescence analysis?

Yes, it includes specialized tools for processing data from platforms like CODEX, Vectra, and MERFISH, including marker quantification and cell segmentation with Mesmer.

PathML Computational Pathology

Name: PathML Computational Pathology
Author: Sologa

bySologa

Ciencia de Datos y ML

Processes and analyzes whole-slide pathology images using advanced machine learning, spatial graph construction, and multiparametric imaging workflows.

Acerca de

PathML is a comprehensive Python toolkit designed for the end-to-end analysis of whole-slide images (WSI) and multiparametric data. It streamlines complex computational pathology tasks such as loading 160+ slide formats, performing Macenko stain normalization, segmenting nuclei with models like HoVer-Net, and building spatial tissue graphs. Whether you are quantifying marker expression in CODEX datasets or training deep learning models for cell-type classification, this skill provides the modular components and best practices needed to build scalable research pipelines within Claude Code.

Características Principales

Spatial analysis through the construction of cell and tissue-level graphs
Automated nucleus segmentation and classification using HoVer-Net and HACTNet
Modular preprocessing pipelines for tissue detection and Macenko/Vahadane stain normalization
Multiparametric support for CODEX, Vectra, and MERFISH spatial proteomics
Unified loading for 160+ whole-slide image formats including SVS, NDPI, and DICOM
0 GitHub stars

Casos de Uso

Managing and training deep learning models on large-scale pathology datasets using HDF5
Developing automated diagnostic pipelines for H&E stained tissue sections
Analyzing spatial proteomics and marker quantification in multiplex immunofluorescence

Acerca de

Características Principales

Spatial analysis through the construction of cell and tissue-level graphs
Automated nucleus segmentation and classification using HoVer-Net and HACTNet
Modular preprocessing pipelines for tissue detection and Macenko/Vahadane stain normalization
Multiparametric support for CODEX, Vectra, and MERFISH spatial proteomics
Unified loading for 160+ whole-slide image formats including SVS, NDPI, and DICOM
0 GitHub stars

Casos de Uso

Managing and training deep learning models on large-scale pathology datasets using HDF5
Developing automated diagnostic pipelines for H&E stained tissue sections
Analyzing spatial proteomics and marker quantification in multiplex immunofluorescence