磁共振成像特征在鉴别痉挛性脑瘫患者GMFCS分级的可行性  

Feasibility of Magnetic Resonance Imaging Features in Identifying Patients with Spastic Cerebral Palsy for GMFCS Classification

作　　者：姜煜 刘港 白惠中 邓博文 李筱叶 任敬佩 赵毅 胡传宇 徐林[1] 穆晓红[1] JIANG Yu;LIU Gang;BAI Hui-zhong;DENG Bo-wen;LI Xiao-ye;REN Jing-pei;ZHAO Yi;HU Chuan-yu;XU Lin;MU Xiao-hong(Department of Orthopedics,Dongzhimen Hospital,Beijing University of Traditional Chinese Medicine,Beijing 100700,China)

机构地区：[1]北京中医药大学东直门医院骨四科,北京100700

出　　处：《中国CT和MRI杂志》2024年第5期28-31,共4页Chinese Journal of CT and MRI

摘　　要：目的在这项研究中,我们旨在利用小腿三头肌MRI构建影像组学模型,实现区分GMFCSⅠ-Ⅴ级SCP患者。方法本研究收集GMFCSⅣ-Ⅴ级SCP患者16例和GMFCSⅠ-Ⅲ级SCP患者40例。利用小腿MRI的T2加权成像进行分析。人工分割小腿三头肌后,对图像特征采用LASSO回归等方法进行筛选,利用线性模型LR、KNN、树模型XGBoost和深度学习模型MLP四种方法进行建模并评估模型性能。结果Log-sigma-20mm-3D firstordermaximum、Log-sigma-20mm 3D glcm-Idn、Wavelet-LLH-glszm-SizeZoneNonUniformity是可区分GMFCS分级的核心特征。评估模型性能时,在XGBoost模型中表现异常出色,在训练数据集中的AUC为0.981,但在测试数据集中降至0.729。它在测试数据集中具有高灵敏度(0.958)和特异性(0.923)。使用Hosmer-Lemeshow检验评估模型拟合时,除KNN模型外,所有模型在训练和测试队列中均表现出大于0.05的p值,展示模型在预测结果的可靠性和有效性。使用决策曲线分析(DCA)对每个模型进行了全面评估,同样展示显著优势。结论通过小腿三头肌MRI影像组学构建GMFCS分级诊断模型是一项有前途的方法,在提高GMFCS分级判断精准性具有一定意义。Objective GMFCS grading is the main grading method for evaluating the level of motor function in spastic cerebral palsy and is widely used in clinical decision making.However,how to improve the precision of GMFCS grading judgment is an important issue.In this study,we aimed to construct an imaging histology model using calf triceps MRI to achieve differentiation between GMFCS grades I-V in patients with SCP.Methods With the approval of the Ethics Committee,16 patients with GMFCS grade IV-V SCP(10 males and 6 females)and 40 patients with GMFCS grade I-III SCP(28 males and 12 females)were collected in this study.T2-weighted imaging using calf MRI was utilized for analysis.After manually segmenting the calf triceps,the image features were screened using methods such as LASSO regression,and four methods,namely,the linear model LR,KNN,the tree model XGBoost,and the deep learning model MLP,were used to model and evaluate the model performance.Results Log-sigma-20mm-3D firstorder-maximum,Log-sigma-20mm 3D glcm-Idn,and Wavelet-LLH-glszm-SizeZoneNonUniformity are the core features that can differentiate the GMFCS classification.When evaluating the model performance,it performs exceptionally well in the XGBoost model,with an AUC of 0.981 in the training dataset,but drops to 0.729 in the test dataset.it has high sensitivity(0.958)and specificity(0.923)in the test dataset.When assessing model fit using the Hosmer-Lemeshow test,all models except the KNN model exhibited p-values greater than 0.05 in both the training and test cohorts,demonstrating the reliability and validity of the models in predicting outcomes.Each model was fully evaluated using Decision Curve Analysis(DCA),again demonstrating significant advantages.Conclusion Constructing a diagnostic model for GMFCS grading by calf triceps MRI imaging histology is a promising approach with implications in improving the precision of GMFCS grading judgments.

关 键 词：影像组学 脑性瘫痪 核磁共振:GMFCS分级 

分 类 号：R742.3[医药卫生—神经病学与精神病学] R445.2[医药卫生—临床医学]