Researchers have developed a new probabilistic framework to quantify uncertainty in deformable image registration (DIR) for radiotherapy. This method models the deformation at each voxel as a random variable, allowing for the calculation of dose probabilities, expected doses, and confidence bounds. The framework is designed to be computationally efficient and interpretable, avoiding complex biomechanical models. It was demonstrated on a prostate cancer case study, showing that the design of certainty maps significantly impacts dose uncertainty more than the choice of probability kernel. AI
IMPACT Provides a transparent method for incorporating image registration uncertainty into radiotherapy dose assessment.
RANK_REASON The cluster contains an academic paper detailing a new methodology.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
