Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, People's Republic of China.
Department of Radiology, Bishan Hospital of Chongqing Medical University, Chongqing, People's Republic of China.
Medicine (Baltimore). 2024 Mar 1;103(9):e37379. doi: 10.1097/MD.0000000000037379.
The study proposes a combined nomogram based on radiomics features from magnetic resonance neurohydrography and clinical features to identify symptomatic nerves in patients with primary trigeminal neuralgia. We retrospectively analyzed 140 patients with clinically confirmed trigeminal neuralgia. Out of these, 24 patients constituted the external validation set, while the remaining 116 patients contributed a total of 231 nerves, comprising 118 symptomatic nerves, and 113 normal nerves. Radiomics features were extracted from the MRI water imaging (t2-mix3d-tra-spair). Radiomics feature selection was performed using L1 regularization-based regression, while clinical feature selection utilized univariate analysis and multivariate logistic regression. Subsequently, radiomics, clinical, and combined models were developed by using multivariate logistic regression, and a nomogram of the combined model was drawn. The performance of nomogram in discriminating symptomatic nerves was assessed through the area under the curve (AUC) of receiver operating characteristics, accuracy, and calibration curves. Clinical applications of the nomogram were further evaluated using decision curve analysis. Five clinical factors and 13 radiomics signatures were ultimately selected to establish predictive models. The AUCs in the training and validation cohorts were 0.77 (0.70-0.84) and 0.82 (0.72-0.92) with the radiomics model, 0.69 (0.61-0.77) and 0.66 (0.53-0.79) with the clinical model, 0.80 (0.74-0.87), and 0.85 (0.76-0.94) with the combined model, respectively. In the external validation set, the AUCs for the clinical, radiomics, and combined models were 0.70 (0.60-0.79), 0.78 (0.65-0.91), and 0.81 (0.70-0.93), respectively. The calibration curve demonstrated that the nomogram exhibited good predictive ability. Moreover, The decision curve analysis curve indicated shows that the combined model holds high clinical application value. The integrated model, combines radiomics features from magnetic resonance neurohydrography with clinical factors, proves to be effective in identify symptomatic nerves in trigeminal neuralgia. The diagnostic efficacy of the combined model was notably superior to that of the model constructed solely from conventional clinical features.
该研究提出了一种基于磁共振神经水成像的放射组学特征和临床特征的联合列线图，以识别原发性三叉神经痛患者的症状性神经。我们回顾性分析了 140 例经临床证实的三叉神经痛患者。其中 24 例患者构成外部验证集，其余 116 例患者共贡献了 231 条神经，包括 118 条症状性神经和 113 条正常神经。从 MRI 水成像（t2-mix3d-tra-spair）中提取放射组学特征。利用 L1 正则化回归进行放射组学特征选择，利用单因素分析和多因素逻辑回归进行临床特征选择。然后，利用多因素逻辑回归建立放射组学、临床和联合模型，并绘制联合模型的列线图。通过接收者操作特征曲线（AUC）、准确性和校准曲线评估列线图区分症状性神经的性能。进一步使用决策曲线分析评估列线图的临床应用。最终选择了 5 个临床因素和 13 个放射组学特征来建立预测模型。在训练集和验证集中，放射组学模型的 AUC 分别为 0.77（0.70-0.84）和 0.82（0.72-0.92），临床模型的 AUC 分别为 0.69（0.61-0.77）和 0.66（0.53-0.79），联合模型的 AUC 分别为 0.80（0.74-0.87）和 0.85（0.76-0.94）。在外部验证集中，临床、放射组学和联合模型的 AUC 分别为 0.70（0.60-0.79）、0.78（0.65-0.91）和 0.81（0.70-0.93）。校准曲线表明该列线图具有良好的预测能力。此外，决策曲线分析曲线表明联合模型具有较高的临床应用价值。该综合模型结合了磁共振神经水成像的放射组学特征和临床因素，在识别三叉神经痛的症状性神经方面证明是有效的。联合模型的诊断效能明显优于仅基于常规临床特征构建的模型。
