Stars
The MIDRC Interoperability Tool is a suite of Gen3 mesh software services that enable medical imaging data repositories to participate in a data mesh by sharing data, communicating, and exchanging …
An extremely fast Python package and project manager, written in Rust.
LaB-RAG (Label Boosted Retrieval Augmented Generation): a generalizable framework for captioning using categorical labels as image descriptors.
[VLDB '25] Magneto combines small and large language models to provide cost-effective schema matching.
AI-backed tools for working with data model curation and harmonization
Multimodal Cancer Modeling in the Age of Foundation Model Embeddings
The documentation repository for the dbGaP FHIR API.
AI-powered CLI tool for transforming data formats (e.g., TOPMED) into LinkML or Phenopackets, including LinkML schema generation and validation.
A toolkit for synthetic phenotype data generation. Particularly for use in synthesizing topmed data.
GDC Cohort Copilot is an AI copilot tool to assist in the curation of cohorts from the NCI GDC using natural language.
Advanced Privacy-Preserving Federated Learning framework
A Model Context Protocol (MCP) server for interacting with Gen3 data commons.
Data dictionary for the TB project in the NIAID Commons project
Data dictionary for the Charlie project in the NIAID Commons project
A package to simplify common tasks one might perform when interacting with The Cancer Imaging Archive (TCIA) via Python.
The Universal Discovery Interface Grammar.
The data dictionary for the Head & Neck Cancer AI pilot.
Notebooks for working with The Cancer Imaging Archive datasets. Have you written one? Submit a PR!
Data, notebooks, and articles associated with the RSNA AI Deep Learning Lab at RSNA 2024
BIH Data Commons using Gen3.2
Deployment of the Gen3 stack on a Kubernetes cluster using the K3s distribution on Ubuntu 22.04
MIDRC-REACT Representativeness Exploration and Comparison Tool
Usagi is an application to help create mappings between coding systems and the Vocabulary standard concepts.
The data dictionary for the MIDRC BDF Imaging Hub.
This project looks at creating a controlled vocabulary for DICOM Pt 6 Data Dictionary with a focus on CS code strings.