Scholarlink

<p>While a constant relative biological effectiveness (RBE) of 1.1 is applied in clinical proton therapy, longstanding clinical concern and <i>in vitro</i> evidence demonstrate a variable proton RBE. Several RBE models for protons have been developed based on general assumptions of RBE dependencies together with fitting to <i>in vitro</i> data, for which some modelling authors have included greater diversity of cell types than others. In this study we use neural networks (NNs) to model the proton RBE without any predefined dependencies, investigate the effect of using different biological inputs and combinations of input parameters in the modelling, and compare the results to previous approaches. A comprehensive <i>in vitro</i> RBE database of 431 data points was used, including parameter values for the proton linear energy transfer (LET), the (α/β)<sub>x</sub> value of the linear quadratic model parameters of the reference photon radiation, and survival fraction (SF)-specific photon doses (D<sub>x</sub>(SF)). NNs were used to model RBEs at specific SFs (RBE<sub>SF</sub>) as a function of (1) LET, (2) LET and (α/β)<sub>x</sub> and (3) LET, (α/β)<sub>x</sub> and D<sub>x</sub>(SF). Models with inputs LET, (α/β)<sub>x</sub> and D<sub>x</sub>(SF) showed overall best performance, particularly inputs with D<sub>x</sub>(0.1) and D<sub>x</sub>(0.2), indicating that an appropriate standardized input parameter for D<sub>x</sub>(SF) could be established by choosing an SF between 0.1 and 0.2. The presented approach to assumption-free NN-based modelling of proton RBE showed similar RBE dependencies as previously published models with similar predictive power. Further, it was demonstrated that adding the photon dose sensitivity as an input parameter to modelling could increase the quality of RBE models.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Neural network modelling of proton RBE values at predominant survival fractions of in vitro data

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月22日

查看全文
  • Erlend Lyngholm,
  • Armin Lühr,
  • Liheng Tian,
  • Camilla Hanquist Stokkevåg,
  • Helge Henjum,
  • Andreas Havsgård Handeland,
  • Johannes Tjelta,
  • Kristian Smeland Ytre-Hauge

摘要

While a constant relative biological effectiveness (RBE) of 1.1 is applied in clinical proton therapy, longstanding clinical concern and in vitro evidence demonstrate a variable proton RBE. Several RBE models for protons have been developed based on general assumptions of RBE dependencies together with fitting to in vitro data, for which some modelling authors have included greater diversity of cell types than others. In this study we use neural networks (NNs) to model the proton RBE without any predefined dependencies, investigate the effect of using different biological inputs and combinations of input parameters in the modelling, and compare the results to previous approaches. A comprehensive in vitro RBE database of 431 data points was used, including parameter values for the proton linear energy transfer (LET), the (α/β)x value of the linear quadratic model parameters of the reference photon radiation, and survival fraction (SF)-specific photon doses (Dx(SF)). NNs were used to model RBEs at specific SFs (RBESF) as a function of (1) LET, (2) LET and (α/β)x and (3) LET, (α/β)x and Dx(SF). Models with inputs LET, (α/β)x and Dx(SF) showed overall best performance, particularly inputs with Dx(0.1) and Dx(0.2), indicating that an appropriate standardized input parameter for Dx(SF) could be established by choosing an SF between 0.1 and 0.2. The presented approach to assumption-free NN-based modelling of proton RBE showed similar RBE dependencies as previously published models with similar predictive power. Further, it was demonstrated that adding the photon dose sensitivity as an input parameter to modelling could increase the quality of RBE models.