[论文解读] Machine-learning-based Classification of Lower-grade gliomas and High-grade gliomas using Radiomic Features in Multi-parametric MRI

Ge Cui, Jiwoong Jeong+7 more|arXiv (Cornell University)|Nov 22, 2019

Radiomics and Machine Learning in Medical Imaging参考文献 33被引用 6

一句话总结

本研究提出一种基于多参数磁共振成像（T1、T1c、T2、FLAIR）放射组学特征的机器学习方法，用于分类低级别胶质瘤（LGG）和高级别胶质瘤（HGG）。通过t检验和LASSO进行特征选择，并采用随机森林分类器，该方法实现了91.3%的准确率和0.956的AUC，显示出在胶质瘤分级中具有很高的诊断性能。

ABSTRACT

Objectives: Glioblastomas are the most aggressive brain and central nervous system (CNS) tumors with poor prognosis in adults. The purpose of this study is to develop a machine-learning based classification method using radio-mic features of multi-parametric MRI to classify high-grade gliomas (HGG) and low-grade gliomas (LGG). Methods: Multi-parametric MRI of 80 patients, 40 HGG and 40 LGG, with gliomas from the MICCAI BRATs 2015 training database were used in this study. Each patient's T1, contrast-enhanced T1, T2, and Fluid Attenuated Inversion Recovery (FLAIR) MRIs as well as the tumor contours were provided in the database. Using the given contours, radiomic features from all four multi-parametric MRIs were extracted. Of these features, a feature selection process using two-sample T-test and least absolute shrinkage, selection operator (LASSO), and a feature correlation threshold was applied to various combinations of T1, contrast-enhanced T1, T2, and FLAIR MRIs separately. These selected features were then used to train, test, and cross-validate a random forest to differentiate HGG and LGG. Finally, the classification accuracy and area under the curve (AUC) were used to evaluate the classification method. Results: Optimized parameters showed that on average, the overall accuracy of our classification method was 0.913 or 73 out of 80 correct classifications, 36/40 for HGG and 37/40 for LGG, with an AUC of 0.956 based on the combination with FLAIR, T1, T1c and T2 MRIs. Conclusion: This study shows that radio-mic features derived from multi-parametric MRI could be used to accurately classify high and lower grade gliomas. The radio-mic features from multi-parametric MRI in combination with even more advanced machine learning methods may further elucidate the underlying tumor biology and response to therapy.

研究动机与目标

• 开发一种非侵入性的、基于机器学习的方法，利用多参数磁共振成像的放射组学特征，对高级别胶质瘤（HGG）与低级别胶质瘤（LGG）进行区分。
• 通过利用定量影像特征，提升胶质瘤分级的准确性，超越传统的放射学评估方法。
• 评估在多个磁共振成像序列（T1、T1c、T2、FLAIR）中，放射组学特征在区分HGG和LGG方面的表现。
• 利用统计与正则化技术，识别出对分类最优的MRI序列及特征组合。
• 展示放射组学与机器学习相结合在提升胶质瘤诊断能力并指导临床决策方面的潜力。

提出的方法

• 从MICCAI BRATS 2015数据库中获取80例胶质瘤患者（40例HGG，40例LGG）的四组MRI序列（T1、增强T1（T1c）、T2和FLAIR）中提取放射组学特征。
• 采用两样本t检验和最小绝对收缩与选择算子（LASSO）进行特征选择，以降低维度并提高模型泛化能力。
• 设定特征相关性阈值，剔除高度相关的特征，防止多重共线性问题。
• 基于单个及组合的MRI序列所选特征，训练随机森林分类器以区分HGG和LGG。
• 采用10折交叉验证评估模型的稳健性，避免过拟合。
• 通过分类准确率和受试者工作特征曲线下面积（AUC）评估模型性能。

实验结果

研究问题

• RQ1 能否利用机器学习方法，通过多参数磁共振成像的放射组学特征准确区分高级别胶质瘤（HGG）与低级别胶质瘤（LGG）？
• RQ2 T1、T1c、T2和FLAIR等MRI序列的何种组合可实现胶质瘤分级的最高分类性能？
• RQ3 t检验和LASSO等特征选择方法在提升分类准确率和减少过拟合方面的有效性如何？
• RQ4 何种放射组学特征集合可使胶质瘤分级的诊断准确率达到最大？
• RQ5 基于放射组学的机器学习模型在多大程度上可超越传统的胶质瘤分级放射学诊断？

主要发现

• 所提出的方法整体分类准确率达到91.3%，正确识别出80例胶质瘤病例中的73例。
• 该模型成功识别出40例HGG中的36例，以及40例LGG中的37例，表明在两种肿瘤分级中均表现出色。
• 受试者工作特征曲线下面积（AUC）达到0.956，显示出HGG与LGG之间极强的判别能力。
• 使用FLAIR、T1、T1c和T2磁共振成像序列组合时性能最佳，凸显多参数成像的价值。
• 采用t检验和LASSO的特征选择方法有效缩小了特征空间，同时保持了高预测准确率。
• 结果表明，多参数磁共振成像的放射组学特征可作为胶质瘤分级可靠的非侵入性生物标志物。