What problem does it solve?
This Skill solves complex computational pathology challenges, enabling efficient analysis of whole-slide images and multiparametric imaging data.
Core Features & Use Cases
- Whole-Slide Image Analysis: Load and process WSI in various formats with automatic image pyramid handling.
- Preprocessing: Build and execute preprocessing pipelines for image manipulation, quality control, and stain normalization.
- Graph Construction: Construct spatial graphs for cell and tissue-level analysis.
- Machine Learning: Train and deploy machine learning models for nucleus detection, segmentation, and classification.
- Multiparametric Imaging: Analyze spatial proteomics and gene expression data from CODEX, Vectra, and MERFISH platforms.
- Data Management: Efficiently store and manage large pathology datasets using HDF5 storage.
- Use Case: If you need to process a large collection of histopathology slides for cancer research, PathML can help you efficiently segment nuclei, analyze tissue structure, and train machine learning models on your data.
Quick Start
Install PathML using the command: uv pip install pathml. Then, load a whole-slide image and preprocess it using the following code:
from pathml.core import SlideData
from pathml.preprocessing import Pipeline, StainNormalizationHE, TissueDetectionHE
wsi = SlideData.from_slide("path/to/slide.svs")
pipeline = Pipeline([
TissueDetectionHE(),
StainNormalizationHE(target='normalize', stain_estimation_method='macenko')
])
pipeline.run(wsi)
