PuSH - Publication Server of Helmholtz Zentrum München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Erdur, A.C.* ; Scholz, D.* ; Nguyen, Q.M.* ; Buchner, J.A.* ; Mayinger, M.* ; Christ, S.M.* ; Brunner, T.B.* ; Wittig, A.* ; Zimmer, C.* ; Meyer, B.* ; Guckenberger, M.* ; Andratschke, N.* ; El Shafie, R.A.* ; Debus, J.U.* ; Rogers, S.* ; Riesterer, O.* ; Schulze, K.* ; Feldmann, H.J.* ; Blanck, O.* ; Zamboglou, C.* ; Bilger-Z, A.* ; Grosu, A.L.* ; Wolff, R.* ; Eitz, K.A. ; Combs, S.E. ; Bernhardt, D.* ; Wiestler, B.* ; Rueckert, D.* ; Peeken, J.C.

Improving risk assessment of local failure in brain metastases patients using vision transformers - A multicentric development and validation study.

Radiother. Oncol. 210:111031 (2025)
Publ. Version/Full Text Research data DOI PMC
Open Access Hybrid
Creative Commons Lizenzvertrag
BACKGROUND AND PURPOSE: 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. MATERIALS AND METHODS: 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. RESULTS: 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. CONCLUSIO: 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.
Impact Factor
Scopus SNIP
Altmetric
0.000
0.000
Tags
Annotations
Special Publikation
Hide on homepage

Edit extra information
Edit own tags
Private
Edit own annotation
Private
Hide on publication lists
on hompage
Mark as special
publikation
Publication type Article: Journal article
Document type Scientific Article
Keywords Artificial Intelligence ; Brain Metastases ; Stereotactic Radiotherapy ; Vision Transformers; Stereotactic Radiosurgery
Language english
Publication Year 2025
HGF-reported in Year 2025
ISSN (print) / ISBN 0167-8140
e-ISSN 1879-0887
Journal Radiotherapy and Oncology
Quellenangaben Volume: 210, Issue: , Pages: , Article Number: 111031 Supplement: ,
Publisher Elsevier
Publishing Place Elsevier House, Brookvale Plaza, East Park Shannon, Co, Clare, 00000, Ireland
Reviewing status Peer reviewed
Institute(s) Institute of Radiation Medicine (IRM)
POF-Topic(s) 30203 - Molecular Targets and Therapies
Research field(s) Radiation Sciences
PSP Element(s) G-501300-001
Grants Deutsche Forschungsgemeinschaft (DFG, German Research foundation)
DOI 10.1016/j.radonc.2025.111031
WOS ID 001540906000001
Scopus ID 105010440158
PubMed ID 40618900
Erfassungsdatum 2025-07-16
[➜Report correction]