This dataset contains 13 converted Ultrasound datasets, part of the OmniMedSeg superset. All datasets are converted to a standardized structure with binary masks for each segmentation target.

BUS_BRA: CC-BY 4.0
BUS_UCLM: CC-BY-NC 4.0
FASS: CC-BY 4.0
HC18: CC-BY 4.0
MMOTU: CC-BY 4.0
MUSCLE_US: CC-BY 4.0
OASBUD: CC-BY-NC 4.0
PSFHS: CC-BY 4.0
TG3K: CC-BY-NC 3.0
TN3K: CC-BY-NC 3.0
100_US: Please see https://www.researchgate.net/publication/307907688_Ultrasound_Liver_Tumor_Datasets_Segmentations for licensing details
BUSI: "Breast Ultrasound dataset can be used to train machine learning models which can classify, detect and segment early signs of masses or micro-calcification in breast cancer. Researchers with interest in classification, detection, and segmentation of breast cancer can utilize this data of breast ultrasound images, combine it with others' datasets, and analyze them for further insights."
DDTI: "available for immediate download for research"

================================================================================
DETAILED INFORMATION BY DATASET

[1] 100_US Please see https://www.researchgate.net/publication/307907688_Ultrasound_Liver_Tumor_Datasets_Segmentations for licensing details

License:

Dataset link: https://www.researchgate.net/publication/307907688_Ultrasound_Liver_Tumor_Datasets_Segmentations
Metadata file: Ultrasound/100_US/metadata.json

Citation (bibtex):
@article{hann2017algorithm,
title={Algorithm guided outlining of 105 pancreatic cancer liver metastases in Ultrasound},
author={Hann, Alexander and Bettac, Lucas and Haenle, Mark M and Graeter, Tilmann and Berger, Andreas W and Dreyhaupt, Jens and Schmalstieg, Dieter and Zoller, Wolfram G and Egger, Jan},
journal={Scientific Reports},
volume={7},
number={1},
pages={12779},
year={2017},
publisher={Nature Publishing Group UK London}
}

[2] BUSI

License: Breast Ultrasound dataset can be used to train machine learning models which can classify, detect and segment early signs of masses or micro-calcification in breast cancer. Researchers with interest in classification, detection, and segmentation of breast cancer can utilize this data of breast ultrasound images, combine it with others' datasets, and analyze them for further insights.
Dataset link: https://scholar.cu.edu.eg/?q=afahmy/pages/dataset
Metadata file: Ultrasound/BUSI/metadata.json

Citation (bibtex):
@article{al2020dataset,
title={Dataset of breast ultrasound images},
author={Al-Dhabyani, Walid and Gomaa, Mohammed and Khaled, Hussien and Fahmy, Aly},
journal={Data in brief},
volume={28},
pages={104863},
year={2020},
publisher={Elsevier}
}

[3] BUS_BRA

License: CC-BY 4.0
Dataset link: https://zenodo.org/records/8231412
Metadata file: Ultrasound/BUS_BRA/metadata.json

Citation (bibtex):
@article{gomez2024bus,
title={BUS-BRA: A breast ultrasound dataset for assessing computer-aided diagnosis systems},
author={G{'o}mez-Flores, Wilfrido and Gregorio-Calas, Maria Julia and Coelho de Albuquerque Pereira, Wagner},
journal={Medical physics},
volume={51},
number={4},
pages={3110--3123},
year={2024},
publisher={Wiley Online Library}
}

[4] BUS_UCLM

License: CC-BY-NC 4.0
Dataset link: https://data.mendeley.com/datasets/7fvgj4jsp7/2
Metadata file: Ultrasound/BUS_UCLM/metadata.json

Citation (bibtex):
@data{Vallez2024BUSUCLM,
author = {Vallez, Noelia and
Bueno, Gloria and
Deniz, Oscar and
Rienda, Miguel Angel and
Pastor, Carlos},
title = {{BUS-UCLM: Breast ultrasound lesion segmentation dataset}},
year = 2024,
version = {V2},
publisher = {Mendeley Data},
doi = {10.17632/7fvgj4jsp7.2},
url = {https://doi.org/10.17632/7fvgj4jsp7.2}
}

[5] DDTI

License: "available for immediate download for research" " The access to the dataset is open and the user can download the cases"
Dataset link: https://cimalab.unal.edu.co/projects/detail/20/
Metadata file: Ultrasound/DDTI/metadata.json

Citation (bibtex):
@inproceedings{pedraza2015open,
title={An open access thyroid ultrasound image database},
author={Pedraza, Lina and Vargas, Carlos and Narv{'a}ez, Fabi{'a}n and Dur{'a}n, Oscar and Mu{~n}oz, Emma and Romero, Eduardo},
booktitle={10th International symposium on medical information processing and analysis},
volume={9287},
pages={188--193},
year={2015},
organization={SPIE}
}

[6] FASS

License: CC-BY 4.0
Dataset link: https://data.mendeley.com/datasets/4gcpm9dsc3/1
Metadata file: Ultrasound/FASS/metadata.json

Citation (bibtex):
@data{DaCorreggio2023Fetal,
author = {Da Correggio, Karine Souza and
Noya Galluzzo, Roberto and
Santos, Luís Otávio and
Soares Muylaert Barroso, Felipe and
Zimmermann Loureiro Chaves, Thiago and
Sherlley Casimiro Onofre, Alexandre and
von Wangenheim, Aldo},
title = {Fetal Abdominal Structures Segmentation Dataset Using Ultrasonic Images},
year = 2023,
version = {V1},
publisher = {Mendeley Data},
doi = {10.17632/4gcpm9dsc3.1},
url = {https://doi.org/10.17632/4gcpm9dsc3.1}
}

[7] HC18

License: CC-BY 4.0
Dataset link: https://zenodo.org/records/1327317
Metadata file: Ultrasound/HC18/metadata.json

Citation (bibtex):
@article{van2018automated,
title={Automated measurement of fetal head circumference using 2D ultrasound images},
author={van den Heuvel, Thomas LA and de Bruijn, Dagmar and de Korte, Chris L and Ginneken, Bram van},
journal={PloS one},
volume={13},
number={8},
pages={e0200412},
year={2018},
publisher={Public Library of Science San Francisco, CA USA}
}

[8] MMOTU

License: CC-BY 4.0
Dataset link: https://figshare.com/articles/dataset/_zip/25058690?file=44222642
Metadata file: Ultrasound/MMOTU/metadata.json

Citation (bibtex):
@article{Li2024,
author = "Lang Li",
title = "{MMOTU dataset}",
year = "2024",
month = "1",
url = "https://figshare.com/articles/dataset/_zip/25058690",
doi = "10.6084/m9.figshare.25058690.v2"
}

[9] MUSCLE_US

License: CC-BY 4.0
Source: 'license' field
Dataset link: https://data.mendeley.com/datasets/3jykz7wz8d/1
Metadata file: Ultrasound/MUSCLE_US/metadata.json

Citation (bibtex):
@article{marzola2021deep,
title={Deep learning segmentation of transverse musculoskeletal ultrasound images for neuromuscular disease assessment},
author={Marzola, Francesco and Van Alfen, Nens and Doorduin, Jonne and Meiburger, Kristen M},
journal={Computers in biology and medicine},
volume={135},
pages={104623},
year={2021},
publisher={Elsevier}
}

[10] OASBUD

License: CC-BY-NC 4.0
Dataset link: https://zenodo.org/records/545928
Metadata file: Ultrasound/OASBUD/metadata.json

Citation (bibtex):
@article{piotrzkowska2017open,
title={Open access database of raw ultrasonic signals acquired from malignant and benign breast lesions},
author={Piotrzkowska-Wr{'o}blewska, Hanna and Dobruch-Sobczak, Katarzyna and Byra, Micha{\l} and Nowicki, Andrzej},
journal={Medical physics},
volume={44},
number={11},
pages={6105--6109},
year={2017},
publisher={Wiley Online Library}
}

[11] PSFHS

License: CC BY 4.0
Dataset link: https://zenodo.org/records/7851339#.ZEH6eHZBztU
Metadata file: Ultrasound/PSFHS/metadata.json

Citation (bibtex):
@dataset{Jieyun2023PubicSymphysis,
author = {Jieyun, B. and
ZhanHong, O.},
title = {Pubic Symphysis-Fetal Head Segmentation and
Angle of Progression},
year = 2023,
version = {v1},
publisher = {Zenodo},
doi = {10.5281/zenodo.7851339},
url = {https://doi.org/10.5281/zenodo.7851339}
}

[12] TG3K

License: CC-BY-NC 3.0
Dataset link: https://github.com/haifangong/TRFE-Net-for-thyroid-nodule-segmentation
Metadata file: Ultrasound/TG3K/metadata.json

Citation (bibtex):
@article{gong2023thyroid,
title={Thyroid region prior guided attention for ultrasound segmentation of thyroid nodules},
author={Gong, Haifan and Chen, Jiaxin and Chen, Guanqi and Li, Haofeng and Li, Guanbin and Chen, Fei},
journal={Computers in biology and medicine},
volume={155},
pages={106389},
year={2023},
publisher={Elsevier}
}

[13] TN3K

License: CC-BY-NC 3.0
Dataset link: https://github.com/haifangong/TRFE-Net-for-thyroid-nodule-segmentation
Metadata file: Ultrasound/TN3K/metadata.json

Citation (bibtex):
@article{gong2023thyroid,
title={Thyroid region prior guided attention for ultrasound segmentation of thyroid nodules},
author={Gong, Haifan and Chen, Jiaxin and Chen, Guanqi and Li, Haofeng and Li, Guanbin and Chen, Fei},
journal={Computers in biology and medicine},
volume={155},
pages={106389},
year={2023},
publisher={Elsevier}
}

================================================================================
IMPORTANT NOTES

• All datasets listed are publicly available
• Full metadata is stored in each dataset's metadata.json file
• For CC0-licensed datasets, attribution is appreciated but not required