Xu Junqi, Ren Yan, Zhao Xueying, Wang Xiaoqing, Yu Xuchen, Yao Zhenwei, Zhou Yan, Feng Xiaoyuan, Zhou Xiaohong Joe, Wang He
Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China.
Radiology Department, Hua Shan Hospital, Fudan University, Shanghai, China.
Quant Imaging Med Surg. 2022 Nov;12(11):5171-5183. doi: 10.21037/qims-22-145.
Accurate grading of gliomas is a challenge in imaging diagnosis. This study aimed to evaluate the performance of a machine learning (ML) approach based on multiparametric diffusion-weighted imaging (DWI) in differentiating low- and high-grade adult gliomas.
A model was developed from an initial cohort containing 74 patients with pathology-confirmed gliomas, who underwent 3 tesla (3T) diffusion magnetic resonance imaging (MRI) with 21 b values. In all, 112 histogram features were extracted from 16 parameters derived from seven diffusion models [monoexponential, intravoxel incoherent motion (IVIM), diffusion kurtosis imaging (DKI), fractional order calculus (FROC), continuous-time random walk (CTRW), stretched-exponential, and statistical]. Feature selection and model training were performed using five randomly permuted five-fold cross-validations. An internal test set (15 cases of the primary dataset) and an external cohort (n=55) imaged on a different scanner were used to validate the model. The diagnostic performance of the model was compared with that of a single DWI model and DWI radiomics using accuracy, sensitivity, specificity, and the area under the curve (AUC).
Seven significant multiparametric DWI features (two from the stretched-exponential and FROC models, and three from the CTRW model) were selected to construct the model. The multiparametric DWI model achieved the highest AUC (0.84, versus 0.71 for the single DWI model, P<0.05), an accuracy of 0.80 in the internal test, and both AUC and accuracy of 0.76 in the external test.
Our multiparametric DWI model differentiated low- (LGG) from high-grade glioma (HGG) with better generalization performance than the established single DWI model. This result suggests that the application of an ML approach with multiple DWI models is feasible for the preoperative grading of gliomas.
神经胶质瘤的准确分级是影像诊断中的一项挑战。本研究旨在评估基于多参数扩散加权成像（DWI）的机器学习（ML）方法在鉴别成人低级别和高级别神经胶质瘤中的性能。
从一个初始队列中开发了一个模型，该队列包含74例经病理证实的神经胶质瘤患者，这些患者接受了具有21个b值的3特斯拉（3T）扩散磁共振成像（MRI）检查。总共从七个扩散模型（单指数模型、体素内不相干运动（IVIM）、扩散峰度成像（DKI）、分数阶微积分（FROC）、连续时间随机游走（CTRW）、拉伸指数模型和统计模型）导出的16个参数中提取了112个直方图特征。使用五次随机排列的五折交叉验证进行特征选择和模型训练。使用内部测试集（主要数据集中的15例）和在不同扫描仪上成像的外部队列（n = 55）对模型进行验证。使用准确性、敏感性、特异性和曲线下面积（AUC）将模型的诊断性能与单一DWI模型和DWI放射组学的诊断性能进行比较。
选择了七个重要的多参数DWI特征（两个来自拉伸指数模型和FROC模型，三个来自CTRW模型）来构建模型。多参数DWI模型实现了最高的AUC（0.84，单一DWI模型为0.71，P<0.05），内部测试中的准确性为0.80，外部测试中的AUC和准确性均为0.76。
我们的多参数DWI模型在区分低级别（LGG）和高级别神经胶质瘤（HGG）方面具有比既定的单一DWI模型更好的泛化性能。该结果表明，应用具有多个DWI模型的ML方法对神经胶质瘤进行术前分级是可行的。
