naomifridman/BreastDCEDL

BreastDCEDL is a deep learning–ready DCE-MRI dataset of 2,070 breast cancer patients, sourced from I-SPY1, I-SPY2 and the DUKE cohort.

49
/ 100
Emerging

This project provides a comprehensive, standardized dataset of over 2,000 breast cancer patients' dynamic contrast-enhanced MRI (DCE-MRI) scans and harmonized clinical information. It offers both tumor-focused cropped images and full-resolution scans. Researchers and medical AI developers can use this data to train and test machine learning models for breast cancer prognosis and biomarker prediction.

Use this if you are a medical researcher or AI developer working on breast cancer and need a large, high-quality, pre-processed imaging dataset to train predictive models.

Not ideal if you are looking for raw DICOM files or if your research is not focused on breast cancer imaging or machine learning applications.

breast cancer research medical imaging oncology radiology AI clinical trials data
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

22

Forks

8

Language

Jupyter Notebook

License

Last pushed

Feb 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/naomifridman/BreastDCEDL"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.