ImageBR: A Public MRI Dataset for Planned Implant Region and Mammary Gland Segmentation in Breast Reconstruction
Journal of Imaging · 10.11.2026 · 12 (11) · 569
DOI: 10.3390/jimaging12110569 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 10.11.2026. Verfasst von Jianhao Xu und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Guangdong Special Support Program-Science and Technology Innovation Talent Project, Key Laboratory of Guangdong Province.
Abstract (Originalsprache)
Breast magnetic resonance imaging (MRI) offers three-dimensional anatomical information for reconstruction-oriented analysis, but annotated public datasets targeting implant-based reconstruction are limited. ImageBR contains MRI volumes from 44 patients (26 bilateral and 18 unilateral reconstruction cases), yielding 70 breast-level samples with expert annotations of planned implant regions, mammary gland tissue, and breast regions. The planned implant region is a surgeon-defined virtual surgical target rather than a directly visible anatomical structure on MRI, and its reference annotations were established without using the final prosthesis specifications. A two-stage benchmark combines breast-region extraction with an nnU-Net 3D cascade incorporating image-derived anatomical priors and weighted loss optimization. Under patient-level three-fold cross-validation, the reported mean breast-level Dice scores were 83.0% and 74.4% for planned implant region and mammary gland segmentation, respectively. The retrospective comparison of predicted-region volume and diameter with final implanted prosthesis specifications yielded relative errors of 14.27% and 8.98%, respectively, and measures consistency rather than independent implant-selection accuracy.
Förderung
- National Natural Science Foundation of China
- Guangdong Special Support Program-Science and Technology Innovation Talent Project
- Key Laboratory of Guangdong Province
Zitieren
APA
Xu, J., & Xu, X. (2026). ImageBR: A Public MRI Dataset for Planned Implant Region and Mammary Gland Segmentation in Breast Reconstruction. Journal of Imaging, 12(11), 569. https://doi.org/10.3390/jimaging12110569
Vancouver
Xu J, Xu X. ImageBR: A Public MRI Dataset for Planned Implant Region and Mammary Gland Segmentation in Breast Reconstruction. Journal of Imaging. 2026;12(11):569. doi:10.3390/jimaging12110569
BibTeX
@article{Xu2026,
author = {Xu, Jianhao and Xu, Xiaowei},
title = {ImageBR: A Public MRI Dataset for Planned Implant Region and Mammary Gland Segmentation in Breast Reconstruction},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {11},
pages = {569},
doi = {10.3390/jimaging12110569}
}
EUVIMED