Automatic planning of head and neck treatment plans

Abstract

Treatment planning is time‐consuming and the outcome depends on the person performing the optimization. A system that automates treatment planning could potentially reduce the manual time required for optimization and could also provide a method to reduce the variation between persons performing radiation dose planning (dosimetrist) and potentially improve the overall plan quality. This study evaluates the performance of the Auto‐Planning module that has recently become clinically available in the Pinnacle3 radiation therapy treatment planning system. Twenty‐six clinically delivered head and neck treatment plans were reoptimized with the Auto‐Planning module. Comparison of the two types of treatment plans were performed using DVH metrics and a blinded clinical evaluation by two senior radiation oncologists using a scale from one to six. Both evaluations investigated dose coverage of target and dose to healthy tissues. Auto‐Planning was able to produce clinically acceptable treatment plans in all 26 cases. Target coverages in the two types of plans were similar, but automatically generated plans had less irradiation of healthy tissue. In 94% of the evaluations, the autoplans scored at least as high as the previously delivered clinical plans. For all patients, the Auto‐Planning tool produced clinically acceptable head and neck treatment plans without any manual intervention, except for the initial target and OAR delineations. The main benefit of the method is the likely improvement in the overall treatment quality since consistent, high‐quality plans are generated which even can be further optimized, if necessary. This makes it possible for the dosimetrist to focus more time on difficult dose planning goals and to spend less time on the more tedious parts of the planning process.PACS number: 87.55.de

Knowledge‐based automated planning for oropharyngeal cancer

“…One step toward automation is knowledge‐based planning (KBP), which comprises a group of methods that learn from historical treatment plans and predict attributes of desirable plans for new patients . KBP predictions can be input into an automated planning engine to produce a treatment plan, but existing methods introduce a new planning paradigm where planners are typically unable to adjust the final plan using familiar inverse planning techniques (e.g., adjusting objective function weights) . Adjustability of plans is the hallmark of the current clinical planning paradigm, where planners alternate between solving an inverse planning problem (IPP) and tuning model parameters like objective function weights, which quantify the relative importance of various objectives that a planner must optimize.…”

Planning comparison of five automated treatment planning solutions for locally advanced head and neck cancer

“…The first reason is the shape of the target that needs to be convex in order to allow the algorithm to efficiently converge on an optimal solution [17]. Earlier publications had shown that RS generated high quality plans in an efficient treatment planning time for convex target geometry [6, 18]. Therefore, each PTV geometry was approximated by a “more convex” or “less concave” geometry depending on the type of the nearest OAR (serial or parallel architecture).…”

“…Auto-Planning (AP), included in Pinnacle 14.0 (Philips Radiation Oncology Systems), is a fully integrated module in the TPS, similar to the “manual” inverse optimizer module and has been previously described [6, 18]. Briefly, Pinnacle AP is a template-knowledge based treatment planning system.…”

An empirical method for automatic determination of maximum number of segments in DMPO-based IMRT for Head and Neck cases

“…For all plans, an equispaced beam configuration was created with seven beams (H&N cases 1-5) and nine beams (H&N cases 6-10). Auto Plan feature 15 available in Pinnacle (Version 9.10.0) was used to drive the optimization process automatically. For all plans, 4 MU and 6 cm 2 were set as the minimum MU and minimum segment size (MSS) constraints, respectively.…”