Department of Nuclear Medicine, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, No. 1277 Jiefang Ave, Wuhan, 430022, China.
Hubei Province Key Laboratory of Molecular Imaging, Wuhan, 430022, China.
Eur J Nucl Med Mol Imaging. 2021 Oct;48(11):3469-3481. doi: 10.1007/s00259-021-05325-z. Epub 2021 Apr 7.
To construct multivariate radiomics models using hybrid F-FDG PET/MRI for distinguishing between Parkinson's disease (PD) and multiple system atrophy (MSA).
Ninety patients (60 with PD and 30 with MSA) were randomized to training and test sets in a 7:3 ratio. All patients underwent F-fluorodeoxyglucose (F-FDG) PET/MRI to simultaneously obtain metabolic images (F-FDG), structural MRI images (T1-weighted imaging (T1WI), T2-weighted imaging (T2WI) and T2-weighted fluid-attenuated inversion recovery (T2/FLAIR)) and functional MRI images (susceptibility-weighted imaging (SWI) and apparent diffusion coefficient). Using PET and five MRI sequences, we extracted 1172 radiomics features from the putamina and caudate nuclei. The radiomics signatures were constructed with the least absolute shrinkage and selection operator algorithm in the training set, with progressive optimization through single-sequence and double-sequence radiomics models. Multivariable logistic regression analysis was used to develop a clinical-radiomics model, combining the optimal multi-sequence radiomics signature with clinical characteristics and SUV values. The diagnostic performance of the models was assessed by receiver operating characteristic and decision curve analysis (DCA).
The radiomics signatures showed favourable diagnostic efficacy. The optimal model comprised structural (T1WI), functional (SWI) and metabolic (F-FDG) sequences (Radscore) with the area under curves (AUCs) of the training and test sets of 0.971 and 0.957, respectively. The integrated model, incorporating Radscore, three clinical symptoms (disease duration, dysarthria and autonomic failure) and SUV, demonstrated satisfactory calibration and discrimination in the training and test sets (0.993 and 0.994, respectively). DCA indicated the highest clinical benefit of the clinical-radiomics integrated model.
The radiomics signature with metabolic, structural and functional information provided by hybrid F-FDG PET/MRI may achieve promising diagnostic efficacy for distinguishing between PD and MSA. The clinical-radiomics integrated model performed best.
构建基于 F-FDG PET/MRI 的多变量放射组学模型，以区分帕金森病（PD）和多系统萎缩（MSA）。
90 例患者（60 例 PD，30 例 MSA）按 7:3 的比例随机分为训练集和测试集。所有患者均行 F-氟代脱氧葡萄糖（F-FDG）PET/MRI 检查，同时获得代谢图像（F-FDG）、结构 MRI 图像（T1 加权成像（T1WI）、T2 加权成像（T2WI）和 T2 加权液体衰减反转恢复（T2/FLAIR））和功能 MRI 图像（磁敏感加权成像（SWI）和表观扩散系数）。我们从壳核和尾状核提取了 1172 个放射组学特征，利用最小绝对值收缩和选择算子算法（LASSO）在训练集中构建放射组学特征，并通过单序列和双序列放射组学模型进行逐步优化。采用多变量逻辑回归分析，结合最佳多序列放射组学特征、临床特征和 SUV 值，建立临床放射组学模型。采用受试者工作特征曲线（ROC）和决策曲线分析（DCA）评估模型的诊断性能。
放射组学特征具有较好的诊断效能。最佳模型由结构（T1WI）、功能（SWI）和代谢（F-FDG）序列组成（Radscore），训练集和测试集的 AUC 分别为 0.971 和 0.957。整合模型，结合 Radscore、三个临床症状（病程、构音障碍和自主神经衰竭）和 SUV，在训练集和测试集均表现出良好的校准和区分能力（0.993 和 0.994）。DCA 表明，临床放射组学整合模型具有最高的临床获益。
基于 F-FDG PET/MRI 的代谢、结构和功能信息的放射组学特征可实现对 PD 和 MSA 的准确诊断。临床放射组学整合模型表现最佳。
