Online RTP Evaluator for SRS: A Single-Institute Experience

Abstract

The fully-automated planning sequences took w15 minutes of optimization time. As shown in Table 1, the resulting clinically-deliverable automated plans were selected by the physician subjects 70% of the time (HOT: 57%, COLD: 13%, Clinical: 30%). Within the 30% of cases where the manually-planned treatments were selected, in 19 out of 43 instances the reviewing physician deemed the differences between the clinical plan and the closest automated plan to be clinically insignificant. In the 24 cases where the manually-planned treatments were preferred, 21 plans were selected because of more aggressive OAR sparing (brainstem, cochlea, or optic nerve) and 3 plans were selected because the manual plans better spared a nearby volume that received prior radiation therapy. Conclusion: In a clear majority (120/144 Z 83%) of cases, automated SRS planning demonstrated superior or equivalent plan quality to existing manual planning processes. Further refinement of algorithms to balance the complex clinical tradeoffs for high-priority OARs and to account for instances of retreatment will likely improve performance even further.