期刊论文

中文

中华放射医学与防护杂志

0254-5098

2023

43

2

101-105

10.3760/cma.j.cn112271-20221021-00416

本校为第一机构

目的利用放射组学特征构建不同的机器学习分类模型,预测盆腔肿瘤调强放疗剂量验证的γ通过率,并探讨最佳预测模型。方法回顾性分析196例盆腔肿瘤调强放疗计划,采用基于模体测量方式的三维剂量验证结果, γ通过率标准为3%/2 mm、10%剂量阈值。提取基于剂量文件的放射组学特征构建预测模型。分别采用随机森林、支持向量机、自适应增强和梯度提升决策树4种机器学习算法,计算曲线下面积(AUC)值、敏感度和特异度,评估4种预测模型的分类性能。结果随机森林、支持向量机、自适应增强、梯度提升决策树模型的灵敏度和特异度分别为0.93、0.85, 0.93、0.96, 0.38、0.69, 0.46、0.46。随机森林模型和自适应增...

Objective:Based on radiomics characteristics, different machine learning classification models are constructed to predict the gamma pass rate of dose verification in intensity-modulated radiotherapy for pelvic tumors, and to explore the best prediction model.Methods:The results of three-dimensional dose verification based on phantom measurement were retrospectively analyzed in 196 patients with pelvic tumor intensity-modulated radiotherapy plans. The gamma pass rate standard was 3%/2 mm and 10% dose threshold. Prediction models were constructed by extracting radiomic features based on dose doc...