Journal Article

DKFZ-2025-01354

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Improving risk assessment of local failure in brain metastases patients using vision transformers - A multicentric development and validation study.

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.DKFZ* ; Bilger-Z, A.DKFZ* ; Grosu, A. L.DKFZ* ; Wolff, R. ; Eitz, K. A.DKFZ* ; Combs, S. E.DKFZ* ; Bernhardt, D.DKFZ* ; Wiestler, B. ; Rueckert, D. ; Peeken, J. C.DKFZ*

2025
Elsevier Science Amsterdam [u.a.]

This record in other databases:  

Please use a persistent id in citations: doi:10.1016/j.radonc.2025.111031

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.

Keyword(s): Artificial Intelligence ; Brain metastases ; Stereotactic radiotherapy ; Vision Transformers

---

Contributing Institute(s):

1. DKTK Koordinierungsstelle Freiburg (FR01)
2. DKTK Koordinierungsstelle München (MU01)

Research Program(s):

1. 899 - ohne Topic (POF4-899) (POF4-899)

Appears in the scientific report 2025

---

Database coverage:
; BIOSIS Previews ; Biological Abstracts ; Clarivate Analytics Master Journal List ; Current Contents - Clinical Medicine ; Ebsco Academic Search ; Essential Science Indicators ; IF >= 5 ; JCR ; Nationallizenz ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection

---