This study compared knowledge-based and deep-learning dose prediction models with clinically approved plans for prostate radiotherapy with focal boosting.The knowledge-based model accurately reproduced clinical plans.Deep-learning predictions showed median variations of 5% (IQR <5%) for bladder and rectum in high-dose regions and 3.8 Gy higher mean dose (IQR 1.2 Gy) for the femoral heads.However, pudendal artery mean doses were 15 Gy higher (IQR: 10-19 Gy) and urethral V 62.4Gy exceeded 50%, above the 2% constraint, likely reflecting their absence in the training dataset.While deep-learning models provide a consistent spatial framework for plan optimization, expert review remains essential.
Piliero et al. (2026) studied this question.