Background/Objectives: In recent years, numerous studies have been published on determining the WHO grade of central nervous system (CNS) tumors using machine learning algorithms. These studies are usually based on magnetic resonance imaging (MRI) and sometimes also on positron emission tomography (PET) images. To date, however, there are virtually no corresponding studies based on routinely generated computed tomography (CT) images. The aim of our proof-of-concept study is to investigate whether machine learning-based tumor diagnosis is also possible using CT images. Methods: We investigate the differentiability of histologically confirmed low-grade and high-grade gliomas. Three conventional machine learning algorithms and a neural net are tested. In addition, we analyze which of the common imaging methods (MRI or CT) appears to be best suited for the diagnostic question under investigation when machine learning algorithms are used. For this purpose, we compare our results based on CT images with numerous studies based on MRI scans. Results: Our best-performing model includes six features and is obtained using univariate analysis for feature preselection and a Naive Bayes approach for model construction. Using independent test data, this model yields a mean AUC of 0.903, a mean accuracy of 0.839, a mean sensitivity of 0.807 and a mean specificity of 0.864. Conclusions: Our results demonstrate that low-grade and high-grade gliomas can be differentiated with high accuracy using machine learning algorithms, not only based on the usual MRI scans, but also based on CT images. In the future, such CT-image-based models can help to further accelerate brain tumor diagnostics and to reduce the number of necessary biopsies.
背景/目的：近年来，已有大量研究利用机器学习算法确定中枢神经系统（CNS）肿瘤的WHO分级。这些研究通常基于磁共振成像（MRI），有时也结合正电子发射断层扫描（PET）图像。然而迄今为止，基于常规计算机断层扫描（CT）图像的相关研究几乎空白。本概念验证研究旨在探讨基于CT图像是否也能实现机器学习驱动的肿瘤诊断。方法：我们研究了经组织学证实的低级别与高级别胶质瘤的可区分性。测试了三种传统机器学习算法及一种神经网络模型。同时，我们分析了在应用机器学习算法时，哪种常见影像学方法（MRI或CT）更适合本研究探讨的诊断问题。为此，我们将基于CT图像的研究结果与大量基于MRI扫描的研究进行了比较。结果：我们性能最优的模型包含六个特征，通过单变量分析进行特征预选，并采用朴素贝叶斯方法构建模型。使用独立测试数据时，该模型平均AUC为0.903，平均准确率0.839，平均灵敏度0.807，平均特异度0.864。结论：我们的研究结果表明，不仅基于常规MRI扫描，基于CT图像也能通过机器学习算法高精度区分低级别与高级别胶质瘤。未来，此类基于CT图像的模型将有助于进一步加速脑肿瘤诊断进程，并减少必要的活检次数。
肿瘤(癌症)患者之家