- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper presents PAC-VMAT, a framework for optimizing radiotherapy plans directly through machine parameters. It uses a differentiable dose engine to compute clinical sensitivities and converts them into fixed credit targets for separate leaf and MU policies. The method aims to produce favorable dose distributions while satisfying mechanical delivery constraints. Experiments on 70 lung and 67 head-and-neck cases show improvements over direct optimization and adapted RL baselines, with additional comparisons to commercial treatment plans.
Critical strengths
-
The paper addresses a practical problem in radiotherapy planning. Optimizing machine parameters directly avoids the mismatch between predicted dose distributions and executable trajectories. I also find the use of physical sensitivities for credit assignment interesting, especially compared with relying on a single plan-level reward.
-
The experimental results are encouraging. The evaluation covers 137 cases across two anatomical sites, and Figure 5 shows improvements over direct machine optimization, including a reduction in lung target hotspot from 67.43 to 64.12 Gy. The attention to mechanical constraints and implementation details also strengthens the work.
Critical weaknesses
-
I have some concerns about dose calculation consistency. Table 1 shows a large discrepancy between Eclipse and PyDoseRT, with the lung target hotspot changing from 63.38 to 112.77 Gy for the commercial reference plans. This may involve normalization or calibration differences, but it makes the comparison with commercial plans difficult to interpret. Independent dose recalculation would be helpful.
-
The contribution of the proposed credit assignment is not fully isolated. The direct optimization baseline differs in update schedules, weighting, and regularization, so the gains cannot be attributed entirely to the fixed credit targets. The RL comparisons are also somewhat limited because the evaluated versions use patient-specific adaptations rather than the original cross-patient training procedures.
Questions for authors
-
What explains the large differences between Eclipse and PyDoseRT dose calculations in Table 1? Are these mainly caused by normalization or machine calibration settings?
-
Have the PAC-optimized plans been recalculated using an independent clinical treatment planning system? If so, do the improvements in target coverage and organ sparing remain?
-
Can the authors compare PAC against direct gradient optimization with matched update schedules, normalization, regularization, and computational budget? This would help isolate the benefit of the proposed credit targets.
-
Are the improvements in organ doses evaluated at comparable target coverage? It would be useful to know whether the reductions remain when the target coverage requirements are held fixed.
-
Could the authors clarify how the RL baselines were adapted, particularly which parts of their original training procedures were removed or changed? How should these results be interpreted relative to the original methods?
-
What is the actual runtime for the 70-step configuration used in the main results? The reported 4.90-minute estimate appears to correspond to only 20 steps.
7 comments
Author Response (W1, Q1, Q2), Part 2: Dose-Engine Consistency and Independent Recalculation
W1 & Q1 & Q2 (continued): Dose-Engine Consistency and Independent Recalculation
Tab. R1 (continued): Cross-Engine Recalculation of GDP-HMM and PAC-VMAT Deliveries Before and After Target-Coverage Scaling
(b) PAC-VMAT delivery
| Metric | Limit | PyDoseRT | ompMC | EGSnrc | pyRadPlan |
|---|---|---|---|---|---|
| Raw PTV D95 before scaling | — | 60.00 ± 0.00 | 52.93 ± 4.02 | 52.49 ± 4.61 | 55.64 ± 3.42 |
| PTV D95 after scaling | ≥ 60 | 60.00 ± 0.00 | 60.00 ± 0.00 | 60.00 ± 0.00 | 60.00 ± 0.00 |
| PTV D0.03cc ↓ | ≤ 72 | 64.12 ± 2.73 | 72.42 ± 3.63 | 73.35 ± 4.34 | 75.00 ± 5.56 |
| Lung–CTV V20 ↓ | ≤ 37 | 19.20 ± 9.05 | 20.19 ± 8.69 | 20.27 ± 8.66 | 20.21 ± 8.70 |
| Lung–CTV mean ↓ | ≤ 20 | 10.39 ± 4.63 | 12.05 ± 5.25 | 12.07 ± 5.20 | 12.27 ± 5.51 |
| Spinal cord D0.03cc ↓ | ≤ 50.5 | 36.37 ± 14.13 | 44.81 ± 19.28 | 45.30 ± 19.33 | 44.32 ± 18.95 |
| Esophagus mean ↓ | < 34 | 15.16 ± 9.49 | 15.53 ± 9.89 | 15.69 ± 9.98 | 15.93 ± 10.00 |
| Heart D66.7% ↓ | < 45 | 1.79 ± 2.81 | 2.26 ± 3.90 | 2.18 ± 3.86 | 2.64 ± 4.03 |
Independent recalculation with ompMC, EGSnrc, and pyRadPlan shows that the 112.77 Gy hotspot is specific to transferring and rescaling the reference trajectories in PyDoseRT. PAC-VMAT maintains competitive target homogeneity and organ sparing across the independent dose calculations.
Takeaway: The Eclipse–PyDoseRT discrepancy reflects cross-engine transfer combined with coverage rescaling, while independent recalculations confirm that PAC-VMAT's plan quality is not specific to PyDoseRT.
[1] Gao et al., “Automating RT Planning at Scale: High Quality Data for AI Training,” 2025.
[2] Simkó et al., “A Physics-Informed, Plug-and-Play Dose Engine for Gradient-Based Radiotherapy Treatment Planning,” 2025.
[3] Zhu et al., “Report of AAPM Task Group 219 on Independent Calculation-Based Dose/MU Verification for IMRT,” 2021.
[4] Chetty et al., “Report of the AAPM Task Group No. 105: Issues Associated with Clinical Implementation of Monte Carlo-Based Photon and Electron External Beam Treatment Planning,” 2007.
[5] Doerner and Caprile, “Technical Note: Parallel Implementation of the EGSnrc Monte Carlo Simulation of Ionizing Radiation Transport Using OpenMP,” 2017.
[6] Kawrakow, “Accurate Condensed History Monte Carlo Simulation of Electron Transport. I. EGSnrc, the New EGS4 Version,” 2000.
[7] Kawrakow and Walters, “Efficient Photon Beam Dose Calculations Using DOSXYZnrc with BEAMnrc,” 2006.
[8] Lobo and Popescu, “Two New DOSXYZnrc Sources for 4D Monte Carlo Simulations of Continuously Variable Beam Configurations, with Applications to RapidArc, VMAT, TomoTherapy and CyberKnife,” 2010.
[9] Wieser et al., “Development of the Open-Source Dose Calculation and Optimization Toolkit matRad,” 2017.
[10] Bortfeld et al., “Decomposition of Pencil Beam Kernels for Fast Dose Calculations in Three-Dimensional Treatment Planning,” 1993.
Author Response (W2, Q3): Comparison with Direct Gradient Optimizers
W2 & Q3: Comparison with Direct Gradient Optimizers
1. Ablations on update schedules and credit targets. Appendix D.8 and Tables 10 and 11 control the update schedule and intermediate credit refresh, showing that neither factor accounts for the main improvement. Table 3 further holds the policy architecture, update schedule, and target-independent regularization fixed to show that learning from explicit credit targets substantially improves upon differentiating the clinical objective directly.
2. Controlled comparison with direct optimizers. We further compare PAC-VMAT with projected-gradient, Adam, and L-BFGS updates under the same initial plan, normalized credit targets, structural regularization, sequential Leaf–MU schedule, mechanical projection, and 70-step dose-evaluation budget.
Tab. R2: Direct Optimizer Comparison at the Same Target Coverage
| Method | PTV D0.03cc ↓ | Lung–CTV mean ↓ | Spinal cord D0.03cc ↓ | Esophagus mean ↓ |
|---|---|---|---|---|
| Projected gradient | 67.84 | 10.81 | 39.42 | 16.08 |
| L-BFGS | 66.45 | 10.73 | 38.36 | 15.79 |
| Adam | 65.88 | 10.64 | 37.82 | 15.62 |
| PAC-VMAT | 64.12 | 10.39 | 36.37 | 15.16 |
Under the same credit targets, regularization, update schedule, and dose-evaluation budget, PAC-VMAT achieves the lowest target hotspot and organ doses across all four endpoints. The comparison isolates the benefit of learning structured updates through shared policy parameters beyond applying the same credit information with direct numerical optimizers.
Takeaway: PAC-VMAT's advantage persists after matching the gradients, update order, regularization, mechanical projection, and computational budget.
Author Response (W1, Q1, Q2), Part 1: Dose-Engine Consistency and Independent Recalculation
We thank the reviewer for the constructive comments and respond to each point below.
1. Cross-engine transfer and coverage rescaling. The two values come from different evaluation conditions. The Eclipse row in Table 1 evaluates the GDP-HMM reference plans in their original commercial environment [1], whereas the Proprietary plans row recalculates the same Leaf and MU trajectories in PyDoseRT without re-optimization. This cross-engine transfer lowers unscaled target coverage, and rescaling the dose by 60/D95 to match target coverage amplifies the hotspot to 112.77 Gy. PAC-VMAT and all primary baselines are optimized and evaluated within PyDoseRT, a commissioned dose engine validated against physical measurements and 181 clinical VMAT plans [2].
2. Independent dose recalculation. We further recalculate the GDP-HMM and PAC-VMAT trajectories with three independent open-source dose engines, using the same CT volumes, structure masks, and machine parameters, following independent calculation-based dose verification practice for IMRT and VMAT [3].
Two engines use Monte Carlo transport, the reference approach for heterogeneous anatomy such as the lung [4]: ompMC, an OpenMP-parallel re-implementation of EGSnrc coupled photon–electron transport [5], and EGSnrc DOSXYZnrc [6, 7], with each arc simulated through its synchronized phase-space source [8]. The third engine, pyRadPlan, is the Python successor of the open-source planning toolkit matRad [9] and computes photon dose with the singular-value-decomposition pencil-beam algorithm [10]. Tab. R1 reports unscaled target coverage alongside dosimetric endpoints evaluated at matched target coverage.
Tab. R1: Cross-Engine Recalculation of GDP-HMM and PAC-VMAT Deliveries Before and After Target-Coverage Scaling
(a) GDP-HMM reference delivery