AI-Based screening for thoracic aortic aneurysms in routine breast MRI

Abstract 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 thor...

Full description

Saved in:
Bibliographic Details
Main Authors: Dimitrios Bounias, Tobit Führes, Luise Brock, Johanna Graber, Lorenz A. Kapsner, Andrzej Liebert, Hannes Schreiter, Jessica Eberle, Dominique Hadler, Dominika Skwierawska, Ralf Floca, Peter Neher, Balint Kovacs, Evelyn Wenkel, Sabine Ohlmeyer, Michael Uder, Klaus Maier-Hein, Sebastian Bickelhaupt
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-59694-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850221778079580160
author Dimitrios Bounias
Tobit Führes
Luise Brock
Johanna Graber
Lorenz A. Kapsner
Andrzej Liebert
Hannes Schreiter
Jessica Eberle
Dominique Hadler
Dominika Skwierawska
Ralf Floca
Peter Neher
Balint Kovacs
Evelyn Wenkel
Sabine Ohlmeyer
Michael Uder
Klaus Maier-Hein
Sebastian Bickelhaupt
author_facet Dimitrios Bounias
Tobit Führes
Luise Brock
Johanna Graber
Lorenz A. Kapsner
Andrzej Liebert
Hannes Schreiter
Jessica Eberle
Dominique Hadler
Dominika Skwierawska
Ralf Floca
Peter Neher
Balint Kovacs
Evelyn Wenkel
Sabine Ohlmeyer
Michael Uder
Klaus Maier-Hein
Sebastian Bickelhaupt
author_sort Dimitrios Bounias
collection DOAJ
description Abstract 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.
format Article
id doaj-art-ac677e5859244cedb971b95f57623b97
institution OA Journals
issn 2041-1723
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-ac677e5859244cedb971b95f57623b972025-08-20T02:06:36ZengNature PortfolioNature Communications2041-17232025-06-0116111610.1038/s41467-025-59694-2AI-Based screening for thoracic aortic aneurysms in routine breast MRIDimitrios Bounias0Tobit Führes1Luise Brock2Johanna Graber3Lorenz A. Kapsner4Andrzej Liebert5Hannes Schreiter6Jessica Eberle7Dominique Hadler8Dominika Skwierawska9Ralf Floca10Peter Neher11Balint Kovacs12Evelyn Wenkel13Sabine Ohlmeyer14Michael Uder15Klaus Maier-Hein16Sebastian Bickelhaupt17German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Im Neuenheimer Feld 280Radiological Institute, Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3Radiological Institute, Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3Radiological Institute, Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3Radiological Institute, Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3Radiological Institute, Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3Radiological Institute, Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3Radiological Institute, Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3Radiological Institute, Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3Radiological Institute, Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Im Neuenheimer Feld 280German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Im Neuenheimer Feld 280German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Im Neuenheimer Feld 280Radiologie München, Burgstraße 7Radiological Institute, Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3Radiological Institute, Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Im Neuenheimer Feld 280Radiological Institute, Uniklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3Abstract 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.https://doi.org/10.1038/s41467-025-59694-2
spellingShingle Dimitrios Bounias
Tobit Führes
Luise Brock
Johanna Graber
Lorenz A. Kapsner
Andrzej Liebert
Hannes Schreiter
Jessica Eberle
Dominique Hadler
Dominika Skwierawska
Ralf Floca
Peter Neher
Balint Kovacs
Evelyn Wenkel
Sabine Ohlmeyer
Michael Uder
Klaus Maier-Hein
Sebastian Bickelhaupt
AI-Based screening for thoracic aortic aneurysms in routine breast MRI
Nature Communications
title AI-Based screening for thoracic aortic aneurysms in routine breast MRI
title_full AI-Based screening for thoracic aortic aneurysms in routine breast MRI
title_fullStr AI-Based screening for thoracic aortic aneurysms in routine breast MRI
title_full_unstemmed AI-Based screening for thoracic aortic aneurysms in routine breast MRI
title_short AI-Based screening for thoracic aortic aneurysms in routine breast MRI
title_sort ai based screening for thoracic aortic aneurysms in routine breast mri
url https://doi.org/10.1038/s41467-025-59694-2
work_keys_str_mv AT dimitriosbounias aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT tobitfuhres aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT luisebrock aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT johannagraber aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT lorenzakapsner aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT andrzejliebert aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT hannesschreiter aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT jessicaeberle aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT dominiquehadler aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT dominikaskwierawska aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT ralffloca aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT peterneher aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT balintkovacs aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT evelynwenkel aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT sabineohlmeyer aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT michaeluder aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT klausmaierhein aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri
AT sebastianbickelhaupt aibasedscreeningforthoracicaorticaneurysmsinroutinebreastmri