Publications


If you find this dataset useful, please cite our papers:

MLHC 2021 paper introducing TMED-1

The original paper introducing the TMED dataset in 2021.

A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiograms
Zhe Huang, Gary Long, Benjamin Wessler, and Michael C. Hughes
In Proceedings of the 6th Machine Learning for Healthcare (MLHC) conference, 2021.
PDF arXiv PMLR

@inproceedings{huangSemisupervisedEchocardiogramBenchmark2021,
    title = {A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiograms},
    booktitle = {Proceedings of the 6th Machine Learning for Healthcare Conference (MLHC)},
    author = {Huang, Zhe and Long, Gary and Wessler, Benjamin and Hughes, Michael C.},
    year = {2021},
    url = {https://tmed.cs.tufts.edu/papers/HuangEtAl_MLHC_2021.pdf},
}

DataPerf 2022 workshop paper introducing TMED-2

This manuscript introducing our upgraded TMED-2 dataset was accepted for a short talk at the DataPerf workshop co-located with ICML 2022

TMED 2: A Dataset for Semi-Supervised Classification of Echocardiograms
Zhe Huang, Gary Long, Benjamin Wessler, and Michael C. Hughes
Appearing at DataPerf workshop, 2022.
PDF

@inproceedings{huangTMED2Dataset2022,
    title = {TMED 2: A Dataset for Semi-Supervised Classification of Echocardiograms},
    booktitle = {DataPerf workshop at ICML},
    author = {Huang, Zhe and Long, Gary and Wessler, Benjamin and Hughes, Michael C.},
    year = {2022},
    url = {https://tmed.cs.tufts.edu/papers/HuangEtAl_TMED2_DataPerf_2022.pdf},
}

JASE 2023 paper

Demonstrating Automatic AS diagnosis is possible for a clinical audience, with external validation

Automated Detection of Aortic Stenosis Using Machine Learning
Benjamin S. Wessler, Zhe Huang, Gary Long, Stefano Pacifici, Nishant Prashar, Samuel Karmiy, Roman A. Sandler, Joseph Sokol, Daniel B. Sokol, Monica M. Dehn, Luisa Maslon, Eileen Mai, Ayan R. Patel, and Michael C. Hughes
Journal of the American Society of Echocardiography, 2023
Publisher Link PubMed PDF

@article{wesslerAutomatedAS2023,
  author={Wessler, Benjamin S and Huang, Zhe and Long Jr, Gary M and Pacifici, Stefano and Prashar, Nishant and Karmiy, Samuel and Sandler, Roman A and Sokol, Joseph Z and Sokol, Daniel B and Dehn, Monica M and others and Hughes, Michael C},
  journal={Journal of the American Society of Echocardiography},
  year={2023},
  publisher={Elsevier},
  url={https://doi.org/10.1016/j.echo.2023.01.006}
}

AISTATS '23 paper on semi-supervised learning methods

How to perform view classification on ultrasound images using a small labeled training set and large unlabeled set.

Introduces a Heart2Heart benchmark transfering view classifiers from TMED (Boston) to Unity (UK) and CAMUS (France)

Fix-A-Step: Semi-supervised Learning from Uncurated Unlabeled Data
Zhe Huang, Mary-Joy Sidhom, Benjamin S. Wessler, and Michael C. Hughes
Artificial Intelligence and Statistics (AISTATS), 2023
PDF arXiv PMLR

@inproceedings{huangFixAStep2023,
  title={Fix-A-Step: Semi-supervised Learning from Uncurated Unlabeled Data},
  author={Huang, Zhe and Sidhom, Mary-Joy and Wessler, Benjamin S. and Hughes, Michael C},
  booktitle={Artificial Intelligence and Statistics (AISTATS)},
  year={2023},
}

MLHC '23 paper on multiple instance learning methods

How to perform AS diagnosis on ultrasound images with multi-instance learning (MIL) methods, that can coherently aggregate predictions from many individual images.

Detecting Heart Disease from Multi-View Ultrasound Images via Supervised Attention Multiple Instance Learning
Zhe Huang, Benjamin S. Wessler, and Michael C. Hughes
Machine Learning for Healthcare (MLHC), 2023
arXiv Code on GitHub

@inproceedings{huangMLHC2023,
  title={Detecting Heart Disease from Multi-View Ultrasound Images via Supervised Attention Multiple Instance Learning},
  author={Huang, Zhe and Wessler, Benjamin S. and Hughes, Michael C},
  booktitle={Proceedings of the 8th Machine Learning for Healthcare Conference (MLHC)},
  year={2023},
}

CVPR '24 paper on benchmarking self- and semi-supervised methods

Using the view classification task from TMED-2 to benchmark modern methods for learning from limited labeled data.

Systematic comparison of semi-supervised and self-supervised learning for medical image classification
Zhe Huang, Ruijie Jiang, Shuchin Aeron, and Michael C. Hughes
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
PDF at IEEE arXiv Code on GitHub

@inproceedings{huangCVPR2024,
  title={Systematic comparison of semi-supervised and self-supervised learning for medical image classification},
  author={Huang, Zhe and Jiang,Ruijie and Aeron, Shuchin and Michael C. Hughes},
  booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2024},
}