摘要
目的:探讨颈动脉颅外段斑块能谱CT影像组学预测急性缺血性脑卒中(AIS)患者90 d预后的价值。方法:回顾性收集2024年1—12月在昆明医科大学第一附属医院确诊的103例AIS患者的颈动脉能谱CT图像与临床资料。对AIS患者进行90 d随访,将预后良好患者纳入A组(n=58),预后不良患者纳入B组(n=45),分析两组患者颈动脉斑块能谱CT影像组学与临床数据,将单因素P<0.05的指标纳入二元Logistic回归分析,筛选预测AIS患者90 d预后的独立影响因素并建立模型,绘制受试者特征(ROC)曲线评价诊断效能。结果:两组美国国立卫生研究院卒中量表(NIHSS)评分、mean absolute deviation(平均绝对偏差)、high gray level emphasis(长游程高灰度调强)、frequency size(频率大小)、skewness(偏度)、autocorrelation(自相关)比较,差异均有统计学意义(P<0.05)。二元Logistics回归结果显示,frequency size(频率大小)、skewness(偏度)、autocorrelation(自相关)为AIS患者90 d预后的独立影响因素,建立预测模型为Logit(P),其曲线下面积(AUC)为0.923,灵敏度为91.7%,特异度为86.5%。结论:颈动脉颅外段斑块能谱CT影像组学能有效预测AIS患者90 d预后,为临床治疗方案的制定提供参考。
Objective To explore the feasibility of using spectral CT radiomics features of extracranial carotid artery plaques to predict the 90 d prognosis in patients with acute ischemic stroke(AIS).Methods Spectral CT images and clinical data of 103 AIS patients diagnosed at the First Affiffiliated Hospital of Kunming Medical University from January to December 2024 were retrospectively collected.Patients were followed up for 90 d and divided into Group A(favorable prognosis,n=58)and Group B(unfavorable prognosis,n=45).The spectral CT radiomic features and clinical data of carotid artery plaques were compared between the two groups.Indicators with P<0.05 in univariate analysis were included in binary logistic regression analysis to identify independent predictors for the 90 d prognosis in AIS patients.A prediction model was established,and the receiver operating characteristic(ROC)curve was drawn to evaluate diagnostic efficacy.Results Significant differences were found between the two groups in the National Institutes of Health Stroke Scale(NIHSS)score,mean absolute deviation,high gray level emphasis,frequency size,skewness,and autocorrelation(P<0.05).The binary logistic regression results showed that frequency size,skewness,and autocorrelation were independent factors inflfluencing the 90 d prognosis of AIS patients.The established prediction model was Logit(P),with an area under the curve(AUC)of 0.923,a sensitivity of 91.7%,and a specifificity of 86.5%.Conclusions Spectral CT radiomics analysis for extracranial carotid artery plaque can effffectively predict the 90 d prognosis in AIS patients,providing a valuable reference for clinical treatment planning.
作者
梅韬
段慧
臧永洪
廖太斌
李标
MEI Tao;DUAN Hui;ZANG Yonghong;LIAO Taibin;LI Biao(Department of Imaging,the First Affiliated Hospital of Kunming Medical University,Kunming,Yunnan 650032,China;Department of Imaging,Northeast Yunnan Central Hospital,Zhaotong,Yunnan 657000,China)
出处
《影像研究与医学应用》
2026年第4期20-23,共4页
Journal of Imaging Research and Medical Applications
