以生境成像技术提取血肿内亚区域平扫CT影像组学特征预测自发性颅内出血患者血肿增大  

Subregional non-contrast CT radiomics features based on habitat imaging technology for predicting hematoma expansion in patients with spontaneous intracranial hemorrhage

作　　者：卢万俊 袁梦轩 彭剑 孙成团 沈洁玲 高丽清 LU Wanjun;YUAN Mengxuan;PENG Jian;SUN Chengtuan;SHEN Jieling;GAO Liqing(Department of Neurology,Jiangdu People's Hospital Affiliated to Yangzhou University,Yangzhou 225200,China;Department of Radiology,Jiangdu People's Hospital Affiliated to Yangzhou University,Yangzhou 225200,China)

机构地区：[1]扬州大学附属江都人民医院神经内科,江苏扬州225200 [2]扬州大学附属江都人民医院影像科,江苏扬州225200

出　　处：《中国医学影像技术》2023年第12期1792-1797,共6页Chinese Journal of Medical Imaging Technology

摘　　要：目的观察以生境成像技术提取血肿内亚区域平扫CT(NCCT)影像组学特征预测自发性颅内出血(sICH)患者血肿增大(HE)的价值。方法回顾性分析228例传统影像学无明显异常的sICH患者,根据HE与否分为HE组(n=99)与非HE(NHE)组(n=129);同时按8∶2比例划分训练集(n=182)与测试集(n=46)。比较组间临床、NCCT资料及实验室检查结果,以logistic回归分析筛选HE的影响因素。以生境成像技术将血肿ROI聚类划分为3个亚区,提取血肿整体(ROI_(整体))和3个亚区域ROI(ROI_(亚区1)、ROI_(亚区2)、ROI_(亚区3))的影像组学特征(ROI亚区3位于血肿与脑组织临界区)并进行筛选;分别基于4个ROI构建4种预测模型,评估其预测HE效能。结果HE组空腹血糖高于NHE组(t=2.047,P=0.041),但此非sICH HE的独立预测因素(P=0.070)。ROI_(亚区3)影像组学模型预测训练集和测试集sICH HE的曲线下面积分别为0.945和0.863,与同集别ROI_(整体)(0.921、0.813)、ROI_(亚区1)(0.925、0.807)和ROI_(亚区2)影像组学模型(0.909、0.720)差异均无统计学意义(P均>0.05)。决策曲线分析显示,ROI_(亚区域)影像组学模型可较其他3个模型带来更大获益。结论基于生境成像技术提取血肿与脑组织临界区域NCCT影像组学特征对预测sICH患者发生HE具有较高价值。Objective To observe the value of subregional non-contrast CT(NCCT)radiomics features based on habitat imaging technology for predicting hematoma expansion(HE)in patients with spontaneous intracranial hemorrhage(sICH).Methods Data of 228 sICH patients with negative conventional imaging signs were retrospectively analyzed and divided into HE group(n=99)or non HE(NHE)group(n=129)based on the occurrence of HE nor not,also divided into training set(n=182)or test set(n=46)at a ratio of 8∶2.Clinical data,NCCT data and laboratory examination results were compared between groups.Logistic regressive analysis was performed to screen the impact factors of HE.ROI of whole hematoma(ROI_(whole))was sketched and clustered into 3 sub-regions(ROI_(sub1),ROI_(sub2)and ROI_(sub3),the latter located in the critical area between hematoma and brain tissue)with habitat imaging technology,and radiomics features of ROI were extracted and screened.Then 4 prediction models were constructed based on the above 4 ROI,and the efficacy of each model for predicting HE was analyzed.Results The fasting blood glucose in HE group was higher than that in NHE group(t=2.047,P=0.041),which was not independent impact factor for predicting HE in sICH patients(P=0.070)according to logistic regression analysis.The area under the curve of ROI_(sub3)radiomics model for predicting sICH HE in training and test set was 0.945 and 0.863,respectively,not significantly different with that of ROI_(whole)(0.921,0.813),ROI_(sub1)(0.925,0.807)nor ROI_(sub2)(0.909,0.720)(all P>0.05).Decision curve analysis showed that ROI sub3 radiomics model could bring greater benefits than the other 3 models.Conclusion NCCT radiomics features of the critical area between hematoma and brain tissue based on habitat imaging technology had high value for predicting HE in sICH patients.

关 键 词：脑出血 血肿 影像组学 体层摄影术 X线计算机 

分 类 号：R743.34[医药卫生—神经病学与精神病学] R814.42[医药卫生—临床医学]