pathml
Full-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be simpler.
Security Assessment
About pathml
PathML is a comprehensive computational pathology toolkit designed to streamline the analysis of whole-slide images (WSI) and enhance machine learning applications in pathology. By providing an integrated framework, PathML addresses the complexities of handling various proprietary slide formats, enabling researchers and clinicians to efficiently load, preprocess, and analyze large datasets of pathology images. The skill is particularly valuable for tasks such as nucleus segmentation, tissue graph construction, and multiparametric imaging analysis, which are critical in advancing diagnostic and research capabilities in pathology.
FAQ
What slide formats does PathML support?
PathML supports over 160 slide formats including Aperio SVS, Hamamatsu NDPI, Leica SCN, Zeiss ZVI, DICOM, and OME-TIFF.
Can I use PathML for machine learning model training?
Yes, PathML allows for the training and deployment of deep learning models, including pre-built models like HoVer-Net and HACTNet.
What are the main preprocessing capabilities of PathML?
PathML offers modular preprocessing pipelines for tasks like stain normalization, tissue detection, and noise reduction.
Is there a specific hardware requirement for running PathML?
While specific hardware requirements are not mentioned, using a system compatible with Python and PyTorch is essential for optimal performance.
Who are the target users of PathML?
PathML is designed for pathologists, researchers, and data scientists involved in computational pathology and image analysis.
Install pathml
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
K-Dense-AI/claude-scientific-skills