Improving risk assessment of local failure in brain metastases patients using vision transformers - A multicentric development and validation study.
Authors
Affiliations (20)
Affiliations (20)
- Department of Radiation Oncology, TUM School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany; Institute for AI in Medicine and Healthcare, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany. Electronic address: [email protected].
- Institute for AI in Medicine and Healthcare, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany; Department of Neuroradiology, TUM School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany.
- Department of Radiation Oncology, TUM School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany.
- Department of Radiation Oncology, University of Zurich, Zurich, Switzerland.
- Department of Radiation Oncology, University Hospital Magdeburg, Magdeburg, Germany.
- Department of Radiation Oncology, University Hospital W¨urzburg, Julius-Maximilians-University, W¨urzburg, Germany.
- Department of Neuroradiology, TUM School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany.
- Department of Neurosurgery, TUM School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany.
- Department of Radiation Oncology, Heidelberg University Hospital, Heidelberg, Germany; Heidelberg Institute for Radiation Oncology (HIRO), National Center for Radiation Oncology (NCRO), Heidelberg, Germany; Department of Radiation Oncology, University Medical Center G¨ottingen, Göttingen, Germany.
- Department of Radiation Oncology, Heidelberg University Hospital, Heidelberg, Germany; Heidelberg Institute for Radiation Oncology (HIRO), National Center for Radiation Oncology (NCRO), Heidelberg, Germany.
- Radiation Oncology Center KSA-KSB, Kantonsspital Aarau, Aarau, Switzerland.
- Department of Radiation Oncology, General Hospital Fulda, Fulda, Germany.
- Department of Radiation Oncology, University Medical Center Schleswig Holstein, Kiel, Germany; Saphir Radiosurgery Center Frankfurt and Northern Germany, Kiel, Germany.
- Department of Radiation Oncology, University of Freiburg - Medical Center, Freiburg, Germany; German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany; Department of Radiation Oncology, German Oncology Center, European University of Cyprus, Limassol, Cyprus.
- Department of Radiation Oncology, University of Freiburg - Medical Center, Freiburg, Germany; German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany.
- Saphir Radiosurgery Center Frankfurt and Northern Germany, Kiel, Germany; Department of Neurosurgery, University Hospital Frankfurt, Frankfurt, Germany.
- Department of Radiation Oncology, TUM School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany; Deutches Konsortium f¨ur Translationale Krebsforschung (DKTK), Partner Site Munich, Munich, Germany; Institute of Radiation Medicine (IRM), Helmholtz Center Munich, Munich, Germany.
- Department of Radiation Oncology, TUM School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany; Deutches Konsortium f¨ur Translationale Krebsforschung (DKTK), Partner Site Munich, Munich, Germany.
- Institute for AI in Medicine and Healthcare, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany; Department of Computing, Imperial College London, London, United Kingdom.
- Department of Radiation Oncology, TUM School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany; Deutches Konsortium f¨ur Translationale Krebsforschung (DKTK), Partner Site Munich, Munich, Germany; Institute of Radiation Medicine (IRM), Helmholtz Center Munich, Munich, Germany. Electronic address: [email protected].
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.