BreastDCEDL: A Comprehensive Breast Cancer DCE-MRI Dataset and Transformer Implementation for Treatment Response Prediction

TL;DR

This paper introduces BreastDCEDL, a large, standardized breast DCE-MRI dataset, and demonstrates a novel transformer-based model that achieves state-of-the-art treatment response prediction performance.

Contribution

The paper provides the first public, multicenter breast DCE-MRI dataset with standardized annotations and develops the first transformer model for this data type, improving prediction accuracy.

Findings

Transformer model achieved AUC 0.94 for pCR prediction.

Dataset enables reproducible research and model development.

Standardized data improves deep learning analysis in breast cancer imaging.

Abstract

Breast cancer remains a leading cause of cancer-related mortality worldwide, making early detection and accurate treatment response monitoring critical priorities. We present BreastDCEDL, a curated, deep learning-ready dataset comprising pre-treatment 3D Dynamic Contrast-Enhanced MRI (DCE-MRI) scans from 2,070 breast cancer patients drawn from the I-SPY1, I-SPY2, and Duke cohorts, all sourced from The Cancer Imaging Archive. The raw DICOM imaging data were rigorously converted into standardized 3D NIfTI volumes with preserved signal integrity, accompanied by unified tumor annotations and harmonized clinical metadata including pathologic complete response (pCR), hormone receptor (HR), and HER2 status. Although DCE-MRI provides essential diagnostic information and deep learning offers tremendous potential for analyzing such complex data, progress has been limited by lack of accessible, public, multicenter datasets. BreastDCEDL addresses this gap by enabling development of advanced models, including state-of-the-art transformer architectures that require substantial training data. To demonstrate its capacity for robust modeling, we developed the first transformer-based model for breast DCE-MRI, leveraging Vision Transformer (ViT) architecture trained on RGB-fused images from three contrast phases (pre-contrast, early post-contrast, and late post-contrast). Our ViT model achieved state-of-the-art pCR prediction performance in HR+/HER2- patients (AUC 0.94, accuracy 0.93). BreastDCEDL includes predefined benchmark splits, offering a framework for reproducible research and enabling clinically meaningful modeling in breast cancer imaging.