A large-scale multicenter breast cancer DCE-MRI benchmark dataset with expert segmentations

Artificial Intelligence (AI) research in breast cancer Magnetic Resonance Imaging (MRI) faces challenges due to limited expert-labeled segmentations. To address this, we present a multicenter dataset of 1506 pre-treatment T1-weighted dynamic contrast-enhanced MRI cases, including expert annotations of primary tumors and non-mass-enhanced regions. The dataset integrates imaging data from four collections in The Cancer Imaging Archive (TCIA), where only 163 cases with expert segmentations were initially available. To facilitate the annotation process, a deep learning model was trained to produce preliminary segmentations for the remaining cases. These were subsequently corrected and verified by 16 breast cancer experts (averaging 9 years of experience), creating a fully annotated dataset. Additionally, the dataset includes 49 harmonized clinical and demographic variables, as well as pre-trained weights for a baseline nnU-Net model trained on the annotated data. This resource addresses a critical gap in publicly available breast cancer datasets, enabling the development, validation, and benchmarking of advanced deep learning models, thus driving progress in breast cancer diagnostics, treatment response prediction, and personalized care.

Authors

Institutions

Publication Details

Journal
Scientific Data
Published
2025-03-19
DOI
https://doi.org/10.1038/s41597-025-04707-4
Citations
33
Primary Topic
Radiomics and Machine Learning in Medical Imaging
Type
article
Field-Weighted Citation Impact
44.89

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A large-scale multicenter breast cancer DCE-MRI benchmark dataset with expert segmentations

Amr Muhammad Abdo Salem, Smriti Joshi, Alessandro Catanese, Kaisar Kushibar et al.
33 citations
Scientific Data
Radiomics and Machine Learning in Medical Imaging
44.89
article

A large-scale multicenter breast cancer DCE-MRI benchmark dataset with expert segmentations

Amr Muhammad Abdo Salem, Smriti Joshi, Alessandro Catanese, Kaisar Kushibar, Javier del Riego, Maciej Bobowicz, Oliver Díaz, Kostas Marias, Richard Osuala, Sara W. Tantawy, Eugen Divjak, Pasant M. Abo-Elhoda, Katerina Nikiforaki, Apostolia Tsirikoglou, Lidia Garrucho, Fredrik Strand, Gordana Ivanac, Fred Prior, Oğuz Lafcı, Laura Igual, Carlos Martín-Isla, Ritse M. Mann, Katarzyna Gwoździewicz, Michail E. Klontzas, Karim Lekadir, Martijn P. A. Starmans, Maria-Laura Cosaka, Shorouq S. Sakrana, Norhan O. Shawky-Abdelfatah, Androniki Kozana, Claire-Anne Reidel, Rosa García-Dosdá, Meltem Gulsun-Akpinar
article en
33 citations

Abstract

Artificial Intelligence (AI) research in breast cancer Magnetic Resonance Imaging (MRI) faces challenges due to limited expert-labeled segmentations. To address this, we present a multicenter dataset of 1506 pre-treatment T1-weighted dynamic contrast-enhanced MRI cases, including expert annotations of primary tumors and non-mass-enhanced regions. The dataset integrates imaging data from four collections in The Cancer Imaging Archive (TCIA), where only 163 cases with expert segmentations were initially available. To facilitate the annotation process, a deep learning model was trained to produce preliminary segmentations for the remaining cases. These were subsequently corrected and verified by 16 breast cancer experts (averaging 9 years of experience), creating a fully annotated dataset. Additionally, the dataset includes 49 harmonized clinical and demographic variables, as well as pre-trained weights for a baseline nnU-Net model trained on the annotated data. This resource addresses a critical gap in publicly available breast cancer datasets, enabling the development, validation, and benchmarking of advanced deep learning models, thus driving progress in breast cancer diagnostics, treatment response prediction, and personalized care.

Scientific DataVol. 12(1)
Ain Shams University (EG), Institució Catalana de Recerca i Estudis Avançats (ES), Karolinska University Hospital (SE), University of Crete (GR), Radboud University Nijmegen (NL), University of Zagreb (HR), University Hospital Dubrava (HR), Radboud University Medical Center (NL), Karolinska Institutet (SE), Hellenic Mediterranean University (GR), Helmholtz Zentrum München (DE), Hospital Universitari i Politècnic La Fe (ES), Corporació Sanitària Parc Taulí (ES), Instituto Alexander Fleming (AR), University Hospital of Heraklion (GR), Erasmus MC Cancer Institute (NL), Hospital Universitari Germans Trias i Pujol (ES), Technical University of Munich (DE), Hacettepe University (TR), Universitat de Barcelona (ES), Gdańsk Medical University (PL), Medical University of Vienna (AT), University of Arkansas for Medical Sciences (US), Foundation for Research and Technology Hellas (GR)
European Commission, Ministerio de Ciencia e Innovación
Openalex Percentile: Top 0%
Radiomics and Machine Learning in Medical Imaging
44.89
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.