Heuristic knowledge-based planning for single-isocenter stereotactic radiosurgery to multiple brain metastases.

PURPOSE

Single-isocenter, volumetric-modulated arc therapy (VMAT) stereotactic radiosurgery (SRS) for multiple brain metastases (multimets) can deliver highly conformal dose distributions and reduce overall patient treatment time compared to other techniques. However, treatment planning for multimet cases is highly complex due to variability in numbers and sizes of brain metastases, as well as their relative proximity to organs-at-risk (OARs). The purpose of this study was to automate the VMAT planning of multimet cases through a knowledge-based planning (KBP) approach that adapts single-target SRS dose predictions to multiple target predictions.

METHODS

Using a previously published artificial neural network (ANN) KBP system trained on single-target, linac-based SRS plans, 3D dose distribution predictions for multimet patients were obtained by treating each brain lesion as a solitary target and subsequently combining individual dose predictions into a single distribution. Spatial dose distributions di(r→) for each of the i = 1…N lesions were merged using the combination function d(r→)=∑iNdin(r→)1/n. The optimal value of n was determined by minimizing root-mean squared (RMS) difference between clinical multimet plans and predicted dose per unit length along the line profile joining each lesion in the clinical cohort. The gradient measure GM=[3/4π]1/3V50%1/3-V100%1/3 is the primary quality metric for SRS plan evaluation at our institution and served as the main comparative metric between clinical plans and the KBP results. A total of 41 previously treated multimet plans, with target numbers ranging from N = 2-10, were used to validate the ANN predictions and subsequent KBP auto-planning routine. Fully deliverable KBP plans were developed by converting predicted dose distribution into patient-specific optimization objectives for the clinical treatment planning system (TPS). Plan parity was maintained through identical arc configuration and target normalization. Overall plan quality improvements were quantified by calculating the difference between SRS quality metrics (QMs): ΔQM = QM  - QM . In addition to GM, investigated QMs were: volume of brain receiving ≥ 10 Gy (V ), volume of brain receiving ≥ 5 Gy (ΔV ), heterogeneity index (HI), dose to 0.1 cc of the brainstem (D ), dose to 1% of the optic chiasm (D ), and interlesion dose (D ). In addition to this quantitative analysis, overall plan quality was assessed via blinded plan comparison of the manual and KBP treatment plans by SRS-specializing physicians.

RESULTS

A dose combination factor of n = 8 yielded an integrated dose profile RMS difference of 2.9% across the 41-patient cohort. Multimet dose predictions exhibited ΔGM = 0.07 ± 0.10 cm against the clinical sample, implying either further normal tissue sparing was possible or that dose predictions were slightly overestimating achievable dose gradients. The latter is the more likely explanation, as this bias vanished when dose predictions were converted to deliverable KBP plans ΔGM = 0.00 ± 0.08 cm. Remaining QMs were nearly identical or showed modest improvements in the KBP sample. Equivalent QMs included: ΔV  = 0.37 ± 3.78 cc, ΔHI = 0.02 ± 0.08 and ΔD  = -2.22 ± 171.4 cGy. The KBP plans showed a greater degree of normal tissue sparing as indicated by brain ΔV  = 4.11± 24.05 cc, brainstem ΔD  = 42.8 ± 121.4 cGy, and chiasm ΔD  = 50.8 ± 83.0 cGy. In blinded review by SRS-specializing physicians, KBP-generated plans were deemed equivalent or superior in 32/41(78.1%) of the cases.

CONCLUSION

Heuristic KBP-driven automated planning in linac-based, single-isocenter treatments for multiple brain metastases maintained or exceeded overall plan quality.