Prescription Value-Based Automatic Optimization of Importance Factors in Inverse Planning

Abstract

Objective:An automatic method for the optimization of importance factors was proposed to improve the efficiency of inverse planning.Methods:The automatic method consists of 3 steps: (1) First, the importance factors are automatically and iteratively adjusted based on our proposed penalty strategies. (2) Then, plan evaluation is performed to determine whether the obtained plan is acceptable. (3) If not, a higher penalty is assigned to the unsatisfied objective by multiplying it by a compensation coefficient. The optimization processes are performed alternately until an acceptable plan is obtained or the maximum iteration N max of step (3) is reached.Results:Tested on 2 kinds of clinical cases and compared with manual method, the results showed that the quality of the proposed automatic plan was comparable to, or even better than, the manual plan in terms of the dose–volume histogram and dose distributions.Conclusions:The proposed algorithm has potential to significantly improve the efficiency of the existing manual adjustment methods for importance factors and contributes to the development of fully automated planning. Especially, the more the subobjective functions, the more obvious the advantage of our algorithm.

A New Radiotherapy Optimization Model Based on Equivalent Uniform Dose

“…The new optimization model was used to solve the inverse problem of fluence map optimization (FMO). A gradient-based optimization algorithm (L-BFGS) was used to solve the large-scale, constrained optimization problem [2,[4][5][6][7]11]. The square roots of the beamlet weights were used as optimized variables to avoid non-physical solutions [2,[4][5][6]11].…”

“…A gradient-based optimization algorithm (L-BFGS) was used to solve the large-scale, constrained optimization problem [2,[4][5][6][7]11]. The square roots of the beamlet weights were used as optimized variables to avoid non-physical solutions [2,[4][5][6]11]. The overall research flow is shown in Fig.…”

“…Compared with physical criteria in the optimization based on organ-based model, biological criteria can comprehensively consider tissue performance and its potential nonlinear radiation effects, and have the potential to predict the biological effects of tumors and normal tissues [8]. Therefore, the study of objective functions based on biological criteria has 2 VOLUME XX, 2017 attracted people's attention [2,[9][10][11][12][13][14][15][16][17][18][19]. Biological criteria include TCP,NTCP and gEUD (generalized equivalent uniform dose).…”

“…[19] used a gEUD-based linear sub-score penalizing relative deviation between the actual and the prescribed gEUD 0 . Gradient-based optimization algorithms are widely used to solve the radiotherapy inverse optimization problems in commercial inverse planning systems(HELIOS and Pinnacle) because of their speed [11]. The major concern when using those algorithms is that the optimization iterations may get trapped in a local minimum.…”

Clinical implementation of deep learning-based automated left breast simultaneous integrated boost radiotherapy treatment planning

“…Over the years, technological development in radiation therapy has brought innovation to both hardware and software tools with new irradiation techniques such as intensity-modulated radiation therapy (IMRT) and volumetric-modulated arc therapy (VMAT), and planning approaches (inverse planning, multi-criteria optimisation). While on the one hand this has led to an overall improvement of plan quality, on the other, the higher complexity of the planning process has engendered drawbacks like increased planning time or larger inter-planner variability [1] , [2] , [3] , [4] , [5] .…”