Radiogenomics of lower-grade gliomas: machine learning-based MRI texture analysis for predicting 1p/19q codeletion status
Radiogenomics of lower-grade gliomas: machine learning-based MRI texture analysis for predicting 1p/19q codeletion status
复制标题
DOI：
10.1007/s00330-019-06492-2
复制
发表时间：
2019-11-05
影响因子：
5.9
通讯作者：
Kilickesmez, Ozgur
中科院分区：
文献类型：
--
作者：
Kocak, Burak;Durmaz, Emine Sebnem;Kilickesmez, Ozgur
目的 使用各种最先进的 ML 算法，评估基于机器学习 (ML) 的 MRI 纹理分析在预测低级别胶质瘤 (LGG) 1p/19q 编码缺失状态方面的潜在价值。材料和方法 在这项回顾性研究中，从公共数据库中纳入了 107 名 LGG 患者。使用 LIFEx 软件从传统 T2 加权和对比增强 T1 加权 MRI 图像中提取纹理特征。使用分层 10 倍交叉验证技术以及少数过采样创建训练和看不见的验证分割。使用共线性分析和特征选择 (ReliefF) 完成降维。使用自适应增强、k 最近邻、朴素贝叶斯、神经网络、随机森林、随机梯度下降和支持向量机完成分类。使用弗里德曼检验和配对事后分析来比较基于曲线下面积 (AUC) 的分类性能。结果 总体而言，ML 算法的预测性能在统计上存在显着差异，chi 2(6) = 26.7，p < 0.001。神经网络、朴素贝叶斯、支持向量机、随机森林和随机梯度下降的性能之间没有统计学上的显着差异，调整p > 0.05。这五种算法的平均 AUC 和准确度值分别为 0.769 至 0.869 和 80.1 至 84%。神经网络的平均排名最高，平均 AUC 和准确度值分别为 0.869 和 83.8%。结论 基于 ML 的 MRI 纹理分析可能是预测 LGG 1p/19q 共缺失状态的一种有前途的非侵入性技术。使用该技术以及各种机器学习算法，超过五分之四的 LGG 可以被正确分类。
Objective To evaluate the potential value of the machine learning (ML)-based MRI texture analysis for predicting 1p/19q codeletion status of lower-grade gliomas (LGG), using various state-of-the-art ML algorithms. Materials and methods For this retrospective study, 107 patients with LGG were included from a public database. Texture features were extracted from conventional T2-weighted and contrast-enhanced T1-weighted MRI images, using LIFEx software. Training and unseen validation splits were created using stratified 10-fold cross-validation technique along with minority over-sampling. Dimension reduction was done using collinearity analysis and feature selection (ReliefF). Classifications were done using adaptive boosting, k-nearest neighbours, naive Bayes, neural network, random forest, stochastic gradient descent, and support vector machine. Friedman test and pairwise post hoc analyses were used for comparison of classification performances based on the area under the curve (AUC). Results Overall, the predictive performance of the ML algorithms were statistically significantly different, chi 2(6) = 26.7, p < 0.001. There was no statistically significant difference among the performance of the neural network, naive Bayes, support vector machine, random forest, and stochastic gradient descent, adjusted p > 0.05. The mean AUC and accuracy values of these five algorithms ranged from 0.769 to 0.869 and from 80.1 to 84%, respectively. The neural network had the highest mean rank with mean AUC and accuracy values of 0.869 and 83.8%, respectively. Conclusions The ML-based MRI texture analysis might be a promising non-invasive technique for predicting the 1p/19q codeletion status of LGGs. Using this technique along with various ML algorithms, more than four-fifths of the LGGs can be correctly classified.