Skip to main content

A package for interacting with, visualizing, and benchmarking the SKM-TEA dataset

Project description

Stanford Knee MRI Multi-Task Evaluation (SKM-TEA) Dataset

Paper | Dataset Download | Dataset Docs | About

The 2021 Stanford Knee MRI with Multi-Task Evaluation (SKM-TEA) dataset pairs raw quantitative MRI (qMRI) data, image data, and dense labels of tissues and pathology for end-to-end exploration and evaluation of the MR imaging pipeline.

This repository contains the building blocks for training and benchmarking models with the SKM-TEA dataset, such as PyTorch dataloaders, evaluation metrics, and baselines. It also contains tutorials for using the dataset and codebase. It utilizes Meddlr and PyTorch Lightning for training, evaluation, and machine utilities.

⚡ QuickStart

pip install skm-tea

Installing locally: For local development, fork and clone the repo and run pip install -e ".[dev]"

_Installing from main: For most up-to-date code without a local install, run pip install "skm-tea @ git+"

Configure your paths and get going!

import meddlr as mr
import os

# (Optional) Configure and save machine/cluster preferences.
# This only has to be done once and will persist across sessions.
cluster = mr.Cluster()
cluster.set(results_dir="/path/to/save/results", data_dir="/path/to/datasets")
# OR set these as environment variables.
os.environ["MEDDLR_RESULTS_DIR"] = "/path/to/save/results"
os.environ["MEDDLR_DATASETS_DIR"] = "/path/to/datasets"

# TODO: Add how to easily fetch dataset.

📝 Documentation

Documentation for downloading and using the SKM-TEA dataset can be found in Benchmarks are constantly evolving - check this repository for up-to-date baselines.

🐘 Model Zoo

A list of pre-trained models can be found here and in Google Drive.

To use them, pass the google drive urls for the config and weights (model) files to st.build_deployment_model:

import skm_tea as st

# Make sure to add "download://" before the url!
model = st.get_model_from_zoo(

✉️ About

This repository is being developed at the Stanford's MIMI Lab. Please reach out to arjundd [at] stanford [dot] edu if you would like to use or contribute to SKM-TEA.

If you use the SKM-TEA dataset or code, please use the following BibTex:

  title={SKM-TEA: A Dataset for Accelerated MRI Reconstruction with Dense Image Labels for Quantitative Clinical Evaluation},
  author={Desai, Arjun D and Schmidt, Andrew M and Rubin, Elka B and Sandino, Christopher Michael and Black, Marianne Susan and Mazzoli, Valentina and Stevens, Kathryn J and Boutin, Robert and Re, Christopher and Gold, Garry E and others},
  booktitle={Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)},

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

skm-tea-0.0.2.tar.gz (134.0 kB view hashes)

Uploaded source

Built Distribution

skm_tea-0.0.2-py2.py3-none-any.whl (70.1 kB view hashes)

Uploaded py2 py3

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page