Digital twin framework cuts adaptive proton therapy reoptimization time to 5.5 minutes in prostate SBRT

A digital twin (DT) framework reduced online adaptive proton-therapy reoptimization time to 5.52±2.94 min vs 17.66±7.93 min for clinical workflows (p not given), while achieving comparable plan quality scores (164.01 vs 161.23) and DIL/CTV V100 coverage >99% in prostate SBRT wit…

• Retrospective study using a database of 43 prostate SBRT cases; the DT framework integrates deep-learning deformable registration, daily CBCT anatomy updates, and knowledge-based plan evaluation to pre-generate probabilistic plans.
• Primary endpoint: mean reoptimization time 5.52 ± 2.94 min (DT) vs 17.66 ± 7.93 min (clinical); plan quality scores 164.01 ± 8.03 vs 161.23 ± 9.50 (p-value not reported). DIL V100 99.27%±0.64%, CTV V100 99.95%±0.07%.
• Single-center, retrospective development with 43 prior cases; no external or prospective validation; plan quality scoring relies on the ProKnow system, not clinical outcomes.

RadPigeon summaries are original and for information only. They are not clinical advice.