skills.rest
RamanEbrahimi
RamanEbrahimiCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

pathml

Processes whole-slide pathology images and trains ML models with PathML and PyTorch.

3|Updated Apr 17, 2026
Search Tags:#machine learning#data management#image analysis#pathology#computational pathology#whole-slide imaging
One-click install
npx skills add https://github.com/RamanEbrahimi/raman-marketplace --skill pathml-ramanebrahimi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pathml
Source: https://github.com/RamanEbrahimi/raman-marketplace/tree/main/plugins/agentic-research/skills/scientific-skills/pathml
Command: npx skills add https://github.com/RamanEbrahimi/raman-marketplace --skill pathml-ramanebrahimi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pathml, torch, numpy, scipy, h5py, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill simplifies computational pathology workflows by providing a toolkit for image analysis, machine learning, and data management of whole-slide pathology images.

Core Features & Use Cases

  • Image Loading & Formats: Load and process whole-slide images in over 160 proprietary formats.
  • Preprocessing Pipelines: Build and apply preprocessing pipelines for stain normalization, tissue detection, and noise reduction.
  • Graph Construction: Construct spatial graphs for cellular and tissue-level relationships and spatial analysis.
  • Machine Learning: Train and deploy deep learning models for nucleus detection, segmentation, and classification.
  • Multiparametric Imaging: Analyze spatial proteomics and gene expression data from CODEX, Vectra, MERFISH, and other platforms.
  • Data Management: Efficiently store and manage large pathology datasets using HDF5 format.
  • Use Case: Imagine you need to analyze a whole-slide image of a tumor sample. Use this Skill to load the image, preprocess it, segment the nuclei, and train a model to classify the cell types.

Quick Start

Use the pathml skill to preprocess the whole-slide image 'tumor_sample.svs' and save the results to 'processed_tumor_sample.h5'.

Frequently Asked Questions about pathml

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I preprocess whole-slide pathology images for machine learning?▼

Preprocess whole-slide pathology images by loading the raw scan files, applying stain normalization, detecting tissue regions, and reducing noise. This ensures the imaging data is clean and standardized before training deep learning models for nucleus detection or cell classification.

Can I load proprietary whole-slide image formats for computational pathology analysis?▼

Yes, you can load and process whole-slide images across over 160 proprietary formats. This broad compatibility allows you to directly ingest diverse clinical scans into your computational pathology workflow without needing separate format conversion tools.

How does HDF5 data management work for large pathology datasets?▼

HDF5 data management stores large pathology datasets efficiently by structuring the extracted image tiles and metadata into a hierarchical format. This approach minimizes memory bottlenecks and enables rapid retrieval when training deep learning models on multiparametric imaging data.

How do I construct spatial graphs for cellular relationships in pathology images?▼

Construct spatial graphs by mapping the coordinates of segmented nuclei and tissue regions to model their physical relationships. This spatial analysis captures the structural connectivity between cells, which is crucial for understanding tumor microenvironments and tissue-level interactions.

Does PyTorch work with computational pathology workflows for deep learning?▼

Yes, PyTorch is a required dependency for running computational pathology workflows. It provides the backend framework needed to train, deploy, and optimize deep learning models for complex image analysis tasks like nucleus segmentation and cell classification.

What is the best way to analyze spatial proteomics data from CODEX and Vectra platforms?▼

Analyze spatial proteomics data from CODEX, Vectra, and MERFISH platforms by loading the multiparametric imaging files, extracting spatial coordinates, and constructing graphs. This workflow allows you to model complex spatial relationships and perform large-scale dataset management simultaneously.

Related Skills

Explore More Software Engineering Skills→
AlterLab-IEUAlterLab-IEU
58

alterlab-pathml

Run end-to-end computational pathology workflows from image loading to ML deployment.

Community
Advanced
hxk622hxk622
8

pyhealth

Develop, test, and deploy machine learning models with clinical data.

Community
Advanced
hxk622hxk622
8

torch_geometric

Develop and train Graph Neural Networks using the PyTorch Geometric library.

Community
Advanced
robotlearning123robotlearning123

histolab

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

Community
Advanced