% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Erdur:302814,
author = {A. C. Erdur and D. Scholz and Q. M. Nguyen and J. A.
Buchner and M. Mayinger and S. M. Christ and T. B. Brunner
and A. Wittig and C. Zimmer and B. Meyer and M. Guckenberger
and N. Andratschke and R. A. El Shafie and J. U. Debus and
S. Rogers and O. Riesterer and K. Schulze and H. J. Feldmann
and O. Blanck and C. Zamboglou$^*$ and A. Bilger-Z$^*$ and
A. L. Grosu$^*$ and R. Wolff and K. A. Eitz$^*$ and S. E.
Combs$^*$ and D. Bernhardt$^*$ and B. Wiestler and D.
Rueckert and J. C. Peeken$^*$},
title = {{I}mproving risk assessment of local failure in brain
metastases patients using vision transformers - {A}
multicentric development and validation study.},
journal = {Radiotherapy and oncology},
volume = {210},
issn = {0167-8140},
address = {Amsterdam [u.a.]},
publisher = {Elsevier Science},
reportid = {DKFZ-2025-01354},
pages = {111031},
year = {2025},
abstract = {This study investigates the use of Vision Transformers
(ViTs) to predict Freedom from Local Failure (FFLF) in
patients with brain metastases using pre-operative MRI
scans. The goal is to develop a model that enhances risk
stratification and informs personalized treatment
strategies.Within the AURORA retrospective trial, patients
(n = 352) who received surgical resection followed by
post-operative stereotactic radiotherapy (SRT) were
collected from seven hospitals. We trained our ViT for the
direct image-to-risk task on T1-CE and FLAIR sequences and
combined clinical features along the way. We employed
segmentation-guided image modifications, model adaptations,
and specialized patient sampling strategies during training.
The model was evaluated with five-fold cross-validation and
ensemble learning across all validation runs. An external,
international test cohort (n = 99) within the dataset was
used to assess the generalization capabilities of the model,
and saliency maps were generated for explainability
analysis.We achieved a competent C-Index score of 0.7982 on
the test cohort, surpassing all clinical, CNN-based, and
hybrid baselines. Kaplan-Meier analysis showed significant
FFLF risk stratification. Saliency maps focusing on the BM
core confirmed that model explanations aligned with expert
observations.Our ViT-based model offers a potential for
personalized treatment strategies and follow-up regimens in
patients with brain metastases. It provides an alternative
to radiomics as a robust, automated tool for clinical
workflows, capable of improving patient outcomes through
effective risk assessment and stratification.},
keywords = {Artificial Intelligence (Other) / Brain metastases (Other)
/ Stereotactic radiotherapy (Other) / Vision Transformers
(Other)},
cin = {FR01 / MU01},
ddc = {610},
cid = {I:(DE-He78)FR01-20160331 / I:(DE-He78)MU01-20160331},
pnm = {899 - ohne Topic (POF4-899)},
pid = {G:(DE-HGF)POF4-899},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:40618900},
doi = {10.1016/j.radonc.2025.111031},
url = {https://inrepo02.dkfz.de/record/302814},
}