Deep learning for gamma map prediction in breast IMRT verification
Eva Ambroa, Pedro Gallego, Jaime Pérez‐Alija, Manuel de la Cruz, Oscar Pera, Jaume Quera, Enric Fernández‐Velilla, Martí Lacruz, Pablo Carrasco, Simone Balocco, Oliver DíazAbstract
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 and , and a categorical map‐level spatial‐agreement analysis between predicted and measured gamma maps.
Results
Predictive performance improved with multimodal integration. The portal‐only model achieved an AUC of 0.77 (95% confidence interval [CI] 0.71–0.82), whereas the fully multimodal configuration reached 0.94 (95% CI 0.92–0.96); the difference was statistically significant in a paired bootstrap test (). Balanced accuracy increased from 0.64 to 0.77. For the fully multimodal model, 87.9% and 94.6% of cases showed agreement between measured and predicted GPR within and , respectively. The categorical map‐level spatial agreement was in fields with measured GPR , indicating that the model reproduced the approximate spatial distribution of failing regions.
Conclusions
Multimodal gamma map prediction improved breast IMRT PSQA performance compared with portal‐only modeling and extended assessment beyond scalar GPR estimation. By providing spatially resolved predictions of failing regions, the proposed approach may support more informative and interpretable pretreatment QA.