Improving efficiency in lung SAbR planning using integrated tools for X-ray based adaptive radiotherapy

Abstract

Purpose: To evaluate the feasibility of translating clinical lung stereotactic ablative radiotherapy (SAbR) templates from Ethos1.1 to Ethos2.0, leveraging new features to facilitate dose fall-off and automate patient-specific beam arrangement. This study aims to streamline planning processes and support broader adoption of online adaptive radiotherapy (ART) for lung SAbR.

Methods: We selected fifteen patients previously treated with adaptive lung SAbR using the Ethos1.1 system, each receiving 40-60 Gy in 5 fractions. Plans were reoptimized in Ethos2.0 using identical parameters (rIMRT) to their clinical counterpart. To evaluate new integrated features, we utilized high-fidelity (HF) mode with and without automatic treatment geometry selection (HF-cIMRT, HF-aIMRT/VMAT). These strategies were compared to assess the impact of Ethos2.0's new features on plan quality and efficiency using RTOG-based metrics and enhanced plan deliverability analysis. Statistical significance was assessed using paired Student's t-tests (α = 0.05).

Results: All plans reoptimized in Ethos2.0 demonstrated acceptable plan quality. No statistically significant differences in maximum organ-at-risk doses were observed between evaluated strategies and the clinical plan. For complex cases, human-selected beam geometry proved superior to automated geometry. HF-enabled plans significantly reduced total monitor units, with HF-aVMAT, HF-cIMRT, and HF-aIMRT reporting 3142.4 ± 997.4 (p < 0.001), 3401.8 ± 516.1 (p < 0.001), and 3225.6 ± 484.2 (p < 0.001) compared to clinical 5424.9 ± 1353.4. A trade-off was observed in conformity index, which was 1.06 ± 0.08 (p = 0.006), 1.05 ± 0.06 (p = 0.003), and 1.03 ± 0.05 (p = 0.05) for HF-aIMRT, HF-cIMRT, and HF-aVMAT plans compared to clinical 1.01 ± 0.03.

Conclusion: Lung SAbR planning strategies can be effectively transitioned from Ethos1.1 to Ethos2.0, improving workflow efficiency with high-fidelity mode and minor adjustments. Automated beam geometry tools enhance planner efficiency for both IMRT and VMAT. To address increased ART workload and staffing demands, leveraging integrated automation tools is essential. The planning strategies presented in this study are straightforward and reproducible for ART-enabled clinics.

Keywords: SAbR; adaptive radiotherapy; automation; lung‐SBRT.

FIGURE 1

RTOG‐based plan metrics including PTV hotspot. Conformity index, gradient index, D2cm(%) and PTV hotspot. Statistical significance to clinical plan is denoted by *. Note that on average all plans demonstrate acceptable CI, GI and D2cm and plan hotspot. HF‐enabled plans typically generate a higher plan hotspot while maintaining sharp‐dose fall off where the automatic VMAT plan demonstrates on average the sharpest fall‐off with increased hotspot.

FIGURE 2

Comparative analysis of gantry angle frequencies in IMRT and control point in VMAT techniques for clinical and automatic algorithm. Polar histograms of angle utilization for all 15 patients. Human‐selected angles prefer to spread out beams to contralateral side to boost conformity whereas the algorithm‐selected angles tend to cluster on the ipsilateral treatment side. This difference highlights the varying strategies between human intuition and algorithmic optimization.

FIGURE 3

Total monitor units and reference plan generation time for all 15 patients. Total MU reported for all patients including clinically treated reference plans. Calculation time bar does not include calculation time for clinical cases, as the emulator and clinical system have different graphical processing unit speeds and is not an appropriate comparison. Note that all Ethos2.0 optimized plans generated lower MU with similar calculation times (not including HF‐aVMAT). The VMAT‐generated cases produced the lowest MUs at the cost of calculation time.

FIGURE 4

Axial views of example patient for each strategy with isodose lines. Corresponding axial slices with isodose lines with identical isodose levels are shown. Additionally, the heart (pink), aorta (purpose), spinal cord (dark green), d2cm (green), ITV (light blue) and PTV (red) are shown. Note that all HF plans feature a larger central 125% hotspot. The 50% IDL is qualitatively similar across all plans, except for the automatically generated IMRT case, where the shape suggests more beams were necessary but still acceptable.

FIGURE 5

Example patient automatic geometry selection versus clinical including corresponding axial isodose lines. Similar arc sector usages are observed in all plans, however, the enhanced‐auto10B plan appears to more closely mimic the human selected field geometry. It is evident that in the corresponding axial isodose lines, this simple enhancement helps greatly improve the 50% RX spill into normal tissues.

FIGURE 6

Visual representation with general optimization layering for dose fall‐off shaping. Note the reduction of total number of constraints and priority level for HF‐enabled mode vs conventional IOE. Additionally, ITV hotspot shaping constraints are weakened compared to conventional as HF natively achieves higher values.

FIGURE 7

Adaptive versus scheduled plan comparison for HF‐cIMRT case. To demonstrate the robustness of our methods, we selected one patient's final fraction who received personalized ultra‐fractionated stereotactic ablative RT (PULSAR) for online emulation. The significantly smaller PTV highlights the high‐fidelity mode's ability to handle large changes. This figure shows the dose cloud shrinking compared to the reference plan, reducing OAR and normal lung doses, with notable gradient improvement near the heart.