A comparative assessment of deep learning and knowledge-based dose prediction models for advanced radiotherapy planning of prostate cancer with focal boosting.

内容摘要

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&#xa0;<&#xa0;5%) for bladder and rectum in high-dose regions and 3.8&#xa0;Gy higher mean dose (IQR 1.2&#xa0;Gy) for the femoral heads. However, pudendal artery mean doses were 15&#xa0;Gy higher (IQR: 10-19&#xa0;Gy) and urethral V62.4Gy 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.