Medical physics
Deep learning for gamma map prediction in breast IMRT verification
By Ambroa E, Gallego P, Pérez-Alija J and 8 others.
Abstract
Background
Patient-specific quality assurance (PSQA) in radiotherapy commonly relies on global gamma passing rate (GPR) metrics, which summarize delivery agreement as a single scalar value and therefore provide limited information about the spatial location of dose delivery discrepancies. Spatial prediction of gamma maps may offer a more informative and interpretable representation of PSQA outcomes.
Purpose
To develop and evaluate a multimodal deep learning framework for predicting two-dimensional gamma maps in breast intensity-modulated radiotherapy (IMRT) verification, using portal dose images, multileaf collimator (MLC) modulation maps, and plan complexity metrics.
Methods
A retrospective single-center dataset of 4707 portal dosimetry fields from 644 breast cancer patients treated with IMRT was analyzed. A U-Net-based encoder-decoder architecture was implemented with dedicated encoders for each input modality and intermediate feature fusion before gamma map prediction. The gamma map was predicted as a three-class categorical output (background, failing, and passing) using a softmax layer with per-pixel argmax decoding. Four configurations were compared: portal-only, portal plus modulation maps, portal plus complexity metrics, and fully multimodal input. Five-fold patient-level cross-validation was used to prevent data leakage. Performance was assessed using receiver operating characteristic analysis with a 90% GPR threshold, standard classification metrics, GPR agreement within ± 3 % and ± 5 % , and a categorical map-level spatial-agreement analysis between predicted and measured gamma maps.