通过事件混合技术对预测的马传导率进行公正的评估
Akito S Koganezawa1,2, Takaaki Matsuura3,4, Daisuke Kawahara1
1Department of Radiation Oncology, Hiroshima University Hospital, Hiroshima, Japan.
Medical physics
|November 27, 2023
概括
这项研究引入了一个无偏的成就评分 (AS) 来评估放射治疗中的马传导率 (GPR) 预测模型. 新的评分方法,使用最佳和最差的极限,允许在不同的系统中进行客观的绩效评估.
科学领域:
- 放射治疗 物理 物理
- 医学物理 医学物理
- 计算瘤学计算瘤学
背景情况:
- 马传导率 (GPR) 的预测模型旨在取代放射治疗中的手动马分析.
- 由于治疗计划系统 (TPS),线性加速器和探测器阵列的变化,现有的模型很难进行比较.
- 需要使用公正的方法来评估和比较GPR预测模型的性能.
研究的目的:
- 开发用于评估GPR预测模型的公正评分方法.
- 为GPR预测引入最佳和最差的性能限制,以标准化评估.
- 为了使GPR预测模型在不同辐射疗法系统中的客观比较.
主要方法:
- 使用200个头和的VMAT计划和ArcCHECK测量开发了一个框架.
- 利用深度学习模型来预测GPR (pDL) 并使用SD,CC,MSE和MAE进行评估.
- 从测量GPR (m) 中生成最佳极限,并使用事件混合 (EM) 技术生成最差极限,以进行公正的评估.
主要成果:
- 成绩评分 (AS) 在四个评估指标中显示出良好的一致性.
- 事件混合技术成功生成了无关联的GPR预测对.
- 深度学习模型显示警报频率 (AF) 为31.5%和63.0%,分别为99%和99.9%的信心水平.
结论:
- 为了评估GPR预测模型,开发了一个公正的成就评分 (AS).
- 通过测量GPR精度和EM技术,成功生成了最佳和最差的极限.
- AS和定义的极限有助于客观的模型评估和精确的辐射疗法目标设定.
更多相关视频
07:31Characterization of Recombination Effects in a Liquid Ionization Chamber Used for the Dosimetry of a Radiosurgical Accelerator
Published on: May 9, 2014
11.9K
10:33Expedited Radiation Biodosimetry by Automated Dicentric Chromosome Identification ADCI and Dose Estimation
Published on: September 4, 2017
15.8K
相关概念视频
Expected Frequencies in Goodness-of-Fit Tests
2.5K
A goodness-of-fit test is conducted to determine whether the observed frequency values are statistically similar to the frequencies expected for the dataset. Suppose the expected frequencies for a dataset are equal such as when predicting the frequency of any number appearing when casting a die. In that case, the expected frequency is the ratio of the total number of observations (n) to the number of categories (k).
2.5K
Wald-Wolfowitz Runs Test II
245
The Wald-Wolfowitz runs test, commonly referred to as the runs test, is a nonparametric test used to assess the randomness of ordered data. The test evaluates the number of runs, which are consecutive sequences of similar elements within the data. If the number of runs is significantly higher or lower than expected, the data is considered non-random, indicating a detectable pattern or structure.
For binary data, runs are identified using symbols such as + and −, or equivalently, 1s and...
For binary data, runs are identified using symbols such as + and −, or equivalently, 1s and...
245
Determination of Expected Frequency
2.2K
Suppose one wants to test independence between the two variables of a contingency table. The values in the table constitute the observed frequencies of the dataset. But how does one determine the expected frequency of the dataset? One of the important assumptions is that the two variables are independent, which means the variables do not influence each other. For independent variables, the statistical probability of any event involving both variables is calculated by multiplying the individual...
2.2K
