PuSH - Publication Server of Helmholtz Zentrum München

Garrucho, L.* ; Kushibar, K.* ; Reidel, C.A.* ; Joshi, S.* ; Osuala, R. ; Tsirikoglou, A.* ; Bobowicz, M.* ; Del Riego, J.* ; Catanese, A.* ; Gwoździewicz, K.* ; Cosaka, M.L.* ; Abo-Elhoda, P.M.* ; Tantawy, S.W.* ; Sakrana, S.S.* ; Shawky-Abdelfatah, N.O.* ; Salem, A.M.A.* ; Kozana, A.* ; Divjak, E.* ; Ivanac, G.* ; Nikiforaki, K.* ; Klontzas, M.E.* ; García-Dosdá, R.* ; Gulsun-Akpinar, M.* ; Lafcı, O.* ; Mann, R.M.* ; Martín-Isla, C.* ; Prior, F.* ; Marias, K.* ; Starmans, M.P.A.* ; Strand, F.* ; Diaz, O.* ; Igual, L.* ; Lekadir, K.*

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

Sci. Data 12:453 (2025)
DOI PMC
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.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
Corresponding Author
Keywords Neoadjuvant Chemotherapy; Information; Prediction
ISSN (print) / ISBN 2052-4463
e-ISSN 2052-4463
Journal Scientific Data
Quellenangaben Volume: 12, Issue: 1, Pages: , Article Number: 453 Supplement: ,
Publisher Nature Publishing Group
Publishing Place London
Non-patent literature Publications
Reviewing status Peer reviewed
Institute(s) Institute for Machine Learning in Biomed Imaging (IML)
Grants Juan de la Cierva fellowship
Ministry of Science and Innovation of Spain
European Union