Graduate School, Guilin Medical University, Guilin, 541002, China.
Department of Radiology, Nanxishan Hospital of Guangxi Zhuang Autonomous Region, Guilin, 541004, China.
BMC Med Imaging. 2024 Sep 27;24(1):257. doi: 10.1186/s12880-024-01431-0.
Aim to validate the diagnostic efficacy of radiomics models for predicting various degrees of cognitive impairment in patients with cerebral small vessel disease (CSVD).
Participants were divided into mild cognitive impairment group (mild-CSVD group) and sever cognitive impairment group (sever-CSVD group) according to Montreal Cognitive Assessment (MoCA) performance, 98 gender-age-education matched subjects served as normal controls. Radiomic features were extracted from the segmented hippocampus using PyRadiomics. The feature preprocessing involved replacing missing values with the mean, applying stratified random sampling to allocate subjects into training (80%) and testing (20%) sets, ensuring balance among the three classes (normal controls, mild-CSVD group, and sever-CSVD group). A feature selection method was applied to identify discriminative radiomic features, with the optimal texture feature chosen for developing diagnostic models. Performance was evaluated in both the training and testing sets using receiver operating characteristic (ROC) curve analysis.
The radiomics model achieved an accuracy of 0.625, an AUC of 0.593, a sensitivity of 0.828, and a specificity of 0.316 in distinguishing mild-CSVD group from normal controls. When distinguishing mild-CSVD group from sever-CSVD group, the radiomics model reached an accuracy of 0.683, an AUC of 0.660, a sensitivity of 0.167, and a specificity of 0.897. Similarly, in distinguishing sever-CSVD group from normal controls, the radiomics model exhibited an accuracy of 0.781, an AUC of 0.818, a sensitivity of 0.538, and a specificity of 0.947.
Radiomics model based on hippocampal texture had disparities in the diagnostic efficacy of radiomics models in predicting various degrees of cognitive impairment in patients with CSVD.
旨在验证基于影像组学的模型在预测脑小血管病（CSVD）患者不同程度认知障碍中的诊断效能。
根据蒙特利尔认知评估（MoCA）表现，将参与者分为轻度认知障碍组（轻度 CSVD 组）和重度认知障碍组（重度 CSVD 组），98 名性别、年龄、教育程度匹配的受试者作为正常对照组。使用 PyRadiomics 从分割的海马体中提取影像组学特征。特征预处理包括用平均值替换缺失值，采用分层随机抽样将受试者分配到训练（80%）和测试（20%）集，以确保三个类别（正常对照组、轻度 CSVD 组和重度 CSVD 组）之间的平衡。应用特征选择方法识别具有判别力的影像组学特征，选择最优纹理特征构建诊断模型。采用受试者工作特征（ROC）曲线分析评估模型在训练集和测试集上的性能。
该影像组学模型在区分轻度 CSVD 组与正常对照组时，其准确率为 0.625，AUC 为 0.593，敏感度为 0.828，特异度为 0.316。在区分轻度 CSVD 组与重度 CSVD 组时，影像组学模型的准确率为 0.683，AUC 为 0.660，敏感度为 0.167，特异度为 0.897。同样，在区分重度 CSVD 组与正常对照组时，影像组学模型的准确率为 0.781，AUC 为 0.818，敏感度为 0.538，特异度为 0.947。
基于海马体纹理的影像组学模型在预测 CSVD 患者不同程度认知障碍中的诊断效能存在差异。
