%0 Journal Article
%A Bounias, Dimitrios
%A Führes, Tobit
%A Brock, Luise
%A Graber, Johanna
%A Kapsner, Lorenz A
%A Liebert, Andrzej
%A Schreiter, Hannes
%A Eberle, Jessica
%A Hadler, Dominique
%A Skwierawska, Dominika
%A Floca, Ralf Omar
%A Neher, Peter
%A Kovacs, Balint
%A Wenkel, Evelyn
%A Ohlmeyer, Sabine
%A Uder, Michael
%A Maier-Hein, Klaus
%A Bickelhaupt, Sebastian
%T AI-Based screening for thoracic aortic aneurysms in routine breast MRI.
%J Nature Communications
%V 16
%N 1
%@ 2041-1723
%C [London]
%I Springer Nature
%M DKFZ-2025-01210
%P 5299
%D 2025
%Z #EA:E230#
%X Prognosis for thoracic aortic aneurysms is significantly worse for women than men, with a higher mortality rate observed among female patients. The increasing use of magnetic resonance breast imaging (MRI) offers a unique opportunity for simultaneous detection of both breast cancer and thoracic aortic aneurysms. We retrospectively validate a fully-automated artificial neural network (ANN) pipeline on 5057 breast MRI examinations from public (Duke University Hospital/EA1141 trial) and in-house (Erlangen University Hospital) data. The ANN, benchmarked against 3D-ground-truth segmentations, clinical reports, and a multireader panel, demonstrates high technical robustness (dice/clDice 0.88-0.91/0.97-0.99) across different vendors and field strengths. The ANN improves aneurysm detection rates by 3.5-fold compared with routine clinical readings, highlighting its potential to improve early diagnosis and patient outcomes. Notably, a higher odds ratio (OR = 2.29, CI: [0.55,9.61]) for thoracic aortic aneurysms is observed in women with breast cancer or breast cancer history, suggesting potential further benefits from integrated simultaneous assessment for cancer and aortic aneurysms.
%K Humans
%K Female
%K Magnetic Resonance Imaging: methods
%K Aortic Aneurysm, Thoracic: diagnostic imaging
%K Aortic Aneurysm, Thoracic: diagnosis
%K Breast Neoplasms: diagnostic imaging
%K Middle Aged
%K Neural Networks, Computer
%K Retrospective Studies
%K Breast: diagnostic imaging
%K Aged
%K Male
%K Mass Screening: methods
%K Adult
%F PUB:(DE-HGF)16
%9 Journal Article
%$ pmid:40506431
%R 10.1038/s41467-025-59694-2
%U https://inrepo02.dkfz.de/record/302012