Automated intensity modulated treatment planning: The expedited constrained hierarchical optimization (ECHO) system

Area of Science:

• Medical Physics
• Radiation Oncology
• Computational Biology

Background:

• Intensity modulated radiation therapy (IMRT) planning is complex and time-consuming.
• Automated planning systems aim to improve efficiency and plan quality.

Purpose of the Study:

• To develop and implement a fully automated approach for IMRT treatment planning using a novel optimization technique.
• To compare the automated plans with manually generated plans.

Main Methods:

• Developed Expedited Constrained Hierarchical Optimization (ECHO) algorithm based on hierarchical constrained optimization.
• Integrated ECHO with a treatment planning system (TPS) via API scripting for automation.
• Incorporated a dose correction loop to account for multileaf collimator and scattering effects.
• Retrospectively generated 75 ECHO plans for paraspinal lesions and compared them with VMAT plans.

Main Results:

• ECHO plans were dosimetrically superior to VMAT plans in tumor coverage, plan conformity, and organ-at-risk sparing.
• Significant improvements observed in PTV D95% (1%), cord max dose (6%), esophagus max dose (14%), and Paddick Conformity Index (15%).
• Negligible increase in skin dose (3%) was noted.

Conclusions:

• Hierarchical constrained optimization provides a powerful and flexible tool for automated IMRT planning.
• The dose correction loop accurately accounts for complex dosimetric effects, improving plan quality.
• ECHO automates the planning process, producing high-quality plans and eliminating trial-and-error.