Use of radiomic features and support vector machine to distinguish Parkinson's disease cases from normal controls
Use of radiomic features and support vector machine to distinguish Parkinson's disease cases from normal controls
复制标题
使用放射组学特征和支持向量机区分帕金森病病例与正常对照
DOI：
10.21037/atm.2019.11.26
复制
发表时间：
2019-12-01
影响因子：
--
通讯作者：
Wang, Jian
中科院分区：
文献类型：
--
作者：
Wu, Yue;Jiang, Jie-Hui;Wang, Jian
背景：帕金森病（PD）是一种不可逆的神经退行性疾病。基于神经影像学的PD诊断通常具有低水平或深度学习特征，这导致难以实现精确分类或解释临床意义。在此，我们的目的是提取高阶功能，通过使用放射组学的方法，并达到可接受的诊断准确性在PD。方法：在这个回顾性多队列研究中，我们收集了F-18-氟脱氧葡萄糖正电子发射断层扫描（F-18-FDG PET）图像和临床规模[统一帕金森氏病评定量表（NIRS）和Hoehn & Yahr规模（H&Y）]从两个队列。来自华山医院的一个队列有91名正常对照（NC）和91名PD患者（UPDRS：22.7 +/- 11.7，H&Y：1.8 +/- 0.8），来自无锡904医院的另一个队列有26名NC和22名PD患者（UPDRS：20.9 +/- 11.6，H&Y：1.7 +/- 0.9）。华山队列通过5重交叉验证用作训练集和测试集，无锡队列用作另一个单独的测试集。在基于图谱的方法识别感兴趣区域（ROI）的基础上，利用自相关和Fisher评分算法提取和选择辐射组特征。支持向量机（SVM）进行了训练，以分类PD和NC的基础上选择的放射组学特征。在对比实验中，我们将我们的方法与传统的体素值方法进行了比较。为了保证鲁棒性，上述过程重复了500次。结果：识别出26个脑ROI。总共提取了6110个放射组学特征。其中30个特征经过特征选择后保留。该方法在华山和无锡测试集中的准确率分别达到90.97%+/- 4.66%和88.08%+/- 5.27%。结论：本研究表明，放射组学特征和支持向量机可用于基于F-18-FDG PET图像区分PD和NC。
Background: Parkinson's disease (PD) is an irreversible neurodegenerative disease. The diagnosis of PD based on neuroimaging is usually with low-level or deep learning features, which results in difficulties in achieving precision classification or interpreting the clinical significance. Herein, we aimed to extract high-order features by using radiomics approach and achieve acceptable diagnosis accuracy in PD.Methods: In this retrospective multicohort study, we collected F-18-fluorodeoxyglucose positron emission tomography (F-18-FDG PET) images and clinical scale [the Unified Parkinson's Disease Rating Scale (UPDRS) and Hoehn & Yahr scale (H&Y)] from two cohorts. One cohort from Huashan Hospital had 91 normal controls (NC) and 91 PD patients (UPDRS: 22.7 +/- 11.7, H&Y: 1.8 +/- 0.8), and the other cohort from Wuxi 904 Hospital had 26 NC and 22 PD patients (UPDRS: 20.9 +/- 11.6, H&Y: 1.7 +/- 0.9). The Huashan cohort was used as the training and test sets by 5-fold cross-validation and the Wuxi cohort was used as another separate test set. After identifying regions of interests (ROIs) based on the atlas-based method, radiomic features were extracted and selected by using autocorrelation and fisher score algorithm. A support vector machine (SVM) was trained to classify PD and NC based on selected radiomic features. In the comparative experiment, we compared our method with the traditional voxel values method. To guarantee the robustness, above processes were repeated in 500 times.Results: Twenty-six brain ROIs were identified. Six thousand one hundred and ten radiomic features were extracted in total. Among them 30 features were remained after feature selection. The accuracies of the proposed method achieved 90.97%+/- 4.66% and 88.08%+/- 5.27% in Huashan and Wuxi test sets, respectively.Conclusions: This study showed that radiomic features and SVM could be used to distinguish between PD and NC based on F-18-FDG PET images.