BreastDCEDL: A Deep Learning–Ready Breast DCE-MRI Dataset

BreastDCEDL: A Dynamic Contrast-Enhanced Breast MRI Dataset demo https://colab.research.google.com/github/naomifridman/BreastDCEDL/blob/main/BrestDCEDL_zenodo_demo.ipynb BreastDCEDL is a curated, deep learning–ready dataset of 3D DCE-MRI scans from 2,070 breast cancer patients across three major clinical trials (I-SPY1, I-SPY2, Duke) available through The Cancer Imaging Archive (TCIA). The dataset includes pre-treatment MRI volumes, 3D tumor segmentations, and harmonized clinical and demographic metadata, including pathologic complete response (pCR), hormone receptor (HR), and HER2 status. This resource supports advanced AI research in breast cancer, enabling training and evaluation of transformer-based and other deep learning models. 2070 patients from TCIA clinical trials3D MRI scans · Tumor segmentations · Clinical metadataLabels: pCR, HR, HER2, age, race 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}} Keywords: breast cancer, DCE-MRI, tumor segmentation, deep learning, clinical metadata, ViT, pCR prediction, pCR,HR,HER2,YCIA,ISPY1,DUKE,ISPY2 License Information This dataset is released under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license. The source data were obtained from The Cancer Imaging Archive (TCIA) under the following licenses: I-SPY 1 (CC BY 3.0), I-SPY 2 (CC BY 4.0), and Duke Breast Cancer MRI (CC BY-NC 4.0). To comply with the most restrictive source license (Duke), this derivative dataset adopts the CC BY-NC 4.0 license. Users may share and adapt the data with appropriate attribution, but commercial use is not permitted. For commercial applications, users should contact the original data providers through TCIA.