From the Departments of Imaging Physics (E.D.H.G., J.S.L., J.D.H., D.T.F.), Neurosurgery (J.S.W., S.S.P.), Pathology (G.N.F.), Neuroradiology (D.S.), and Cancer Systems Imaging (D.S.), University of Texas MD Anderson Cancer Center, Houston, Texas.
University of Texas MD Anderson Cancer Center UTHealth Graduate School of Biomedical Sciences (E.D.H.G.), Houston, Texas.
AJNR Am J Neuroradiol. 2020 Mar;41(3):400-407. doi: 10.3174/ajnr.A6405. Epub 2020 Feb 6.
Gliomas are highly heterogeneous tumors, and optimal treatment depends on identifying and locating the highest grade disease present. Imaging techniques for doing so are generally not validated against the histopathologic criterion standard. The purpose of this work was to estimate the local glioma grade using a machine learning model trained on preoperative image data and spatially specific tumor samples. The value of imaging in patients with brain tumor can be enhanced if pathologic data can be estimated from imaging input using predictive models.
Patients with gliomas were enrolled in a prospective clinical imaging trial between 2013 and 2016. MR imaging was performed with anatomic, diffusion, permeability, and perfusion sequences, followed by image-guided stereotactic biopsy before resection. An imaging description was developed for each biopsy, and multiclass machine learning models were built to predict the World Health Organization grade. Models were assessed on classification accuracy, Cohen κ, precision, and recall.
Twenty-three patients (with 7/9/7 grade II/III/IV gliomas) had analyzable imaging-pathologic pairs, yielding 52 biopsy sites. The random forest method was the best algorithm tested. Tumor grade was predicted at 96% accuracy (κ = 0.93) using 4 inputs (T2, ADC, CBV, and transfer constant from dynamic contrast-enhanced imaging). By means of the conventional imaging only, the overall accuracy decreased (89% overall, κ = 0.79) and 43% of high-grade samples were misclassified as lower-grade disease.
We found that local pathologic grade can be predicted with a high accuracy using clinical imaging data. Advanced imaging data improved this accuracy, adding value to conventional imaging. Confirmatory imaging trials are justified.
胶质瘤是高度异质性肿瘤，最佳治疗方法取决于识别和定位存在的最高级别疾病。用于实现这一目标的成像技术通常未针对组织病理学标准进行验证。本研究旨在使用基于术前图像数据和空间特异性肿瘤样本训练的机器学习模型来估计局部胶质瘤分级。如果可以使用预测模型从成像输入中估计病理数据，则可以提高肿瘤患者的成像价值。
2013 年至 2016 年间，前瞻性临床成像试验纳入了胶质瘤患者。进行解剖、弥散、渗透性和灌注序列的磁共振成像（MRI），然后在切除前进行图像引导立体定向活检。为每个活检制定了影像学描述，并构建了多类机器学习模型以预测世界卫生组织（WHO）分级。模型的评估指标包括分类准确性、Cohen κ、精确性和召回率。
23 名患者（7/9/7 级 II/III/IV 级胶质瘤）具有可分析的影像学-病理学配对，产生 52 个活检部位。随机森林法是测试的最佳算法。使用 4 个输入（T2、ADC、CBV 和动态对比增强成像的转移常数），肿瘤分级的预测准确率为 96%（κ=0.93）。仅使用常规成像，整体准确率降低（整体准确率为 89%，κ=0.79），43%的高级别样本被错误分类为低级别疾病。
我们发现，使用临床影像学数据可以非常准确地预测局部病理分级。高级成像数据提高了这一准确性，为常规成像增加了价值。有理由进行确认性影像学试验。
