Published November 11, 2025 | Version v1
Dataset Open

BreastDCEDL_ISPY2 - DCE MRI dataset 982 cases

  • 1. NF Algorithms & AI

Contributors

Description

BreastDCEDL_ISPY2 Dataset (n=982)

The BreastDCEDL_ISPY2 dataset is a curated subset of the I-SPY2 trial, comprising 982 breast cancer cases with pre-treatment DCE-MRI scans. It includes:

  • DCE-MRI sequences (3–12 time points per scan, typically 7)
  • Derived maps and full 3D tumor segmentations
  • Clinical annotations: pathological complete response (pCR), hormone receptor (HR) status, HER2 status, MammaPrint risk level, and age at screening

Demo: https://github.com/naomifridman/BreastDCEDL/blob/main/ISPY2/BrestDCEDL_ISPY2_demo.ipynb

Citation

@article{fridman2026breastdcedl,
  author    = {Fridman, N. and Solway, B. and Fridman, T. and others},
  title     = {{BreastDCEDL}: A standardized deep learning-ready breast {DCE-MRI} dataset of 2,070 patients},
  journal   = {Scientific Data},
  year      = {2026},
  doi       = {10.1038/s41597-026-06589-6},
  url       = {https://doi.org/10.1038/s41597-026-06589-6}
}

Dataset Specifications

  • Total Patients: 982

  • Total Size: ~54 GB

  • Image Format: NIfTI (.nii.gz)

  • Clinical Centers: 22+ institutions

File Organization

BreastDCEDL_ISPY2/

├── BreastDCEDL_ISPY2_metadata.csv         # Clinical and demographic data

├── dce/                                                               # DCE-MRI sequences

│   ├── ACRIN-6698-102212/

│   │   ├── ACRIN-6698-102212_spy2_vis1_dce_aqc_0.nii.gz   # Pre-contrast

│   │   ├── ACRIN-6698-102212_spy2_vis1_dce_aqc_1.nii.gz   # Post-contrast 1

│   │   ├── ACRIN-6698-102212_spy2_vis1_dce_aqc_2.nii.gz   # Post-contrast 2

│   │   ├── ACRIN-6698-102212_spy2_vis1_dce_aqc_3.nii.gz   # Post-contrast 3

│   │   ├── ACRIN-6698-102212_spy2_vis1_dce_aqc_4.nii.gz   # Post-contrast 4

│   │   ├── ACRIN-6698-102212_spy2_vis1_dce_aqc_5.nii.gz   # Post-contrast 5

│   │   └── ACRIN-6698-102212_spy2_vis1_dce_aqc_6.nii.gz   # Post-contrast 6

│   ├── ACRIN-6698-103939/

│   │   └── ... (3-12 DCE time points, typically 7)

│   └── ... (982 patient directories total)

└── masks/                                  # Tumor segmentations

    ├── ACRIN-6698-102212_spy2_vis1_mask.nii.gz

    ├── ACRIN-6698-103939_spy2_vis1_mask.nii.gz

    └── ... (982 binary mask files)

Data Components

Example of all acquisitions for random 7 patients, whith all the acquisitions.

 

Resources

Demo: https://github.com/naomifridman/BreastDCEDL/blob/main/ISPY2/BrestDCEDL_ISPY2_zenodo_demo.ipynb

Full Methodology: Fridman et al., 2025 - arXiv:2506.12190 https://arxiv.org/abs/2506.12190

Citation

@article{fridman2025breastdcedl, title={BreastDCEDL: A Comprehensive Breast Cancer DCE-MRI Dataset and Transformer Implementation for Treatment Response Prediction}, author={Fridman, Naomi and Solway, Bubby and Fridman, Tomer and Barnea, Itamar and Goldstein, Anat}, journal={arXiv preprint arXiv:2506.12190}, year={2025}, doi={10.48550/arXiv.2506.12190} }

Files

BreastDCEDL_ISPY2 – Full Dataset.pdf

Files (57.9 GB)

Name Size Download all
md5:22b37dde13f09cd3133f5ca5b7f32e4b
1.6 MB Preview Download
md5:d24eb2618cb42c567194b1792befdc24
26.1 MB Download
md5:b4ccf405ef1aadf27775b3621cc77f7b
163.3 kB Preview Download
md5:3fa9c64a90a7acb391f2501a2270eaf7
4.9 GB Download
md5:8ab34dc2fded4d98440c3236cb4a894e
6.3 GB Download
md5:25d59a0a9203253939cc8cc7d44ed991
7.4 GB Download
md5:56cb42464844b8fbb1b45d43bf7f0059
3.1 GB Download
md5:509d2523c2e1d1510ae33aa94f452353
3.1 GB Download
md5:5d269da3fb770411d7b3089aaec61016
5.5 GB Download
md5:6dfb35444031294cfd0a352e3afffa04
2.4 GB Download
md5:63473a98c5027365c226b856bc499cd3
6.1 GB Download
md5:353414e8185d6f621a9f4929679aa0d5
1.9 GB Download
md5:570fab844877cc1455142476f7f23ad0
2.7 GB Download
md5:63617b9cd88f32fe5ca0f88cb31368de
3.2 GB Download
md5:9187ae68cd8904c2c4da49be1c1cc726
4.9 GB Download
md5:7b28c17c80439f83b130912c83afb058
5.1 GB Download
md5:0af48219f89ce05b46c6afc71928a6d8
1.3 GB Download

Additional details

Additional titles

Subtitle
Deep Learning ready DCE MRI 3D dataset 982 cases

Related works

Is described by
Publication: arXiv:2506.12190 (arXiv)
Journal: 10.1038/s41597-026-06589-6 (DOI)
Is supplement to
Dataset: 10.5281/zenodo.17580237 (DOI)

Dates

Available
2025-06

Software

References

  • @article{fridman2026breastdcedl, author = {Fridman, N. and Solway, B. and Fridman, T. and others}, title = {BreastDCEDL: A standardized deep learning-ready breast DCE-MRI dataset of 2,070 patients}, journal = {Scientific Data}, year = {2026}, doi = {10.1038/s41597-026-06589-6}, url = {https://doi.org/10.1038/s41597-026-06589-6} }
  • @misc{fridman2025breastdcedl, title={BreastDCEDL: A Comprehensive Breast Cancer DCE-MRI Dataset and Transformer Implementation for Treatment Response Prediction}, author={Fridman, Naomi and Solway, Bubby and Fridman, Tomer and Barnea, Itamar and Goldstein, Anat}, journal={arXiv preprint arXiv:2506.12190}, year={2025}, doi={10.48550/arXiv.2506.12190} }