Hierarchical transformers like SwinUNETR show better robustness to perturbations in a two-stage fluence map prediction pipeline for IMRT, with smooth degradation under moderate changes but sharp failures under severe ones, and SSIM fails to capture clinically relevant errors.
Openkbp: the open-access knowledge-based planning grand challenge and dataset,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Robustness of Transformer-Based Fluence Map Prediction Under Clinically Realistic Perturbations
Hierarchical transformers like SwinUNETR show better robustness to perturbations in a two-stage fluence map prediction pipeline for IMRT, with smooth degradation under moderate changes but sharp failures under severe ones, and SSIM fails to capture clinically relevant errors.