A plan template-based automation solution using a commercial treatment planning system

Abstract

Purpose: The purpose of this study was to develop an auto-planning platform to be interfaced with a commercial treatment planning system (TPS). The main goal was to obtain robust and high-quality plans for different anatomic sites and various dosimetric requirements.

Methods: Monaco (Elekta, St. Louis, US) was the TPS in this work. All input parameters for inverse planning could be defined in a plan template inside Monaco. A software tool called Robot Framework was used to launch auto-planning trials with updated plan templates. The template modifier external to Monaco was the major component of our auto-planning platform. For current implementation, it was a rule-based system that mimics the trial-and-error process of an experienced planner. A template was automatically updated by changing the optimization constraints based on dosimetric evaluation of the plan obtained in the previous trial, along with the data of the iterative optimization extracted from Monaco. Treatment plans generated by Monaco with all plan evaluation criteria satisfied were considered acceptable, and such plans would be saved for further evaluation by clinicians. The auto-planning platform was validated for 10 prostate and 10 head-and-neck cases in comparison with clinical plans generated by experienced planners.

Results: The performance and robustness of our auto-planning platform was tested with clinical cases of prostate and head and neck treatment. For prostate cases, automatically generated plans had very similar plan quality with the clinical plans, and the bladder volume receiving 62.5 Gy, 50 Gy, and 40 Gy in auto-plans was reduced by 1%, 3%, and 5%, respectively. For head and neck cases, auto-plans had better conformity with reduced dose to the normal structures but slightly higher dose inhomogeneity in the target volume. Remarkably, the maximum dose in the spinal cord and brain stem was reduced by more than 3.5 Gy in auto-plans. Fluence map optimization only with less than 30 trials was adequate to generate acceptable plans, and subsequent optimization for final plans was completed by Monaco without further intervention. The plan quality was weakly dependent on the parameter selection in the initial template and the choices of the step sizes for changing the constraint values.

Conclusion: An automated planning platform to interface with Monaco was developed, and our reported tests showed preliminary results for prostate and head and neck cases.

Keywords: VMAT; auto-planning; inverse planning; template.

FIG. 1

The sensitivity window in Monaco. (Conflicts between constraints and goals).

FIG. 2

The auto‐planning platform.

FIG. 3

Capture of keywords in Robot Framework.

FIG. 4

Spider Plots (a) and (b) of three planning iterations starting from different initial constraints on the OARs. If all spokes of a plot (of the same color) are inside the unit circle, the plan is considered acceptable.

FIG. 5

Display of the detailed flowcharts in the template modifier.

FIG. 6

Illustration of details in the third step (OARs adjustment).

FIG. 7

Demonstration of the initial plan template file editor‐based prior information.

FIG. 8

The whole flowchart of auto‐planning platform.

FIG. 9

Dose distribution comparison of auto (b, d) and clinical (a, c) prostate planning (red line: 67.5 Gy isodose line; cyan line: 45 Gy isodose line; orange line: 40 Gy isodose line).

FIG. 10

Final DVH comparison between auto and clinical prostate plan. DVH, dose–volume histogram.

FIG. 11

Comparison of the isodose distribution of auto (a, c) and clinical (b, d) plans.

FIG. 12

Final DVH comparison between auto and clinical head and neck plans. DVH, dose–volume histogram.

FIG. 13

(a) The flowchart of Erasmus‐iCycle; (b) the flowchart of our auto‐planning.

FIG. 14

Change of dose–volume indices with iteration number for a head and neck case.

FIG. 15

Comparison between FMO and segmentation optimization (without and with rescaling 95% dose coverage to PGTVnx6996). FMO, fluence map optimization.

FIG. 16

The similarity between deep reinforcement learning and auto treatment planning process.