切换至 "中华医学电子期刊资源库"

中华脑血管病杂志(电子版) ›› 2024, Vol. 18 ›› Issue (03) : 215 -223. doi: 10.11817/j.issn.1673-9248.2024.03.004

论著

基于CT平扫的影像组学特征预测急性大脑中动脉闭塞机械取栓术后造影剂外渗的价值
于乐林1, 尚海龙1, 杜红娣1, 王莺1, 王一超1, 徐长贺1, 叶娟1, 赵世伟1, 郑芳慧1, 沈慧2, 沈海林1,()   
  1. 1. 215028 苏州,上海交通大学医学院苏州九龙医院影像科
    2. 215028 苏州,上海交通大学医学院苏州九龙医院神经内科
  • 收稿日期:2023-12-09 出版日期:2024-06-01
  • 通信作者: 沈海林
  • 基金资助:
    2021年苏州九龙医院科研预研基金项目(SZJL202112); 苏州市医学会应用基础研究-医疗卫生(2022YX-Q04)

The value of predicting contrast agent extravasation after mechanical thrombectomy for acute middle cerebral artery occlusion based on radiomics features of non-contrast computed tomography

Lelin Yu1, Hailong Shang1, Hongdi Du1, Ying Wang1, Yichao Wang1, Changhe Xu1, Juan Ye1, Shiwei Zhao1, Fanghui Zheng1, Hui Shen2, Hailin Shen1,()   

  1. 1. Department of Radiology, Suzhou Kowloon Hospital, Shanghai JiaoTong University School of Medicine, Suzhou 215028, China
    2. Department of Neurology, Suzhou Kowloon Hospital, Shanghai JiaoTong University School of Medicine, Suzhou 215028, China
  • Received:2023-12-09 Published:2024-06-01
  • Corresponding author: Hailin Shen
引用本文:

于乐林, 尚海龙, 杜红娣, 王莺, 王一超, 徐长贺, 叶娟, 赵世伟, 郑芳慧, 沈慧, 沈海林. 基于CT平扫的影像组学特征预测急性大脑中动脉闭塞机械取栓术后造影剂外渗的价值[J/OL]. 中华脑血管病杂志(电子版), 2024, 18(03): 215-223.

Lelin Yu, Hailong Shang, Hongdi Du, Ying Wang, Yichao Wang, Changhe Xu, Juan Ye, Shiwei Zhao, Fanghui Zheng, Hui Shen, Hailin Shen. The value of predicting contrast agent extravasation after mechanical thrombectomy for acute middle cerebral artery occlusion based on radiomics features of non-contrast computed tomography[J/OL]. Chinese Journal of Cerebrovascular Diseases(Electronic Edition), 2024, 18(03): 215-223.

目的

探讨基于CT平扫的影像组学特征预测单侧大脑中动脉闭塞性卒中患者血管内机械取栓术造影剂外渗的应用价值。

方法

收集2015年12月至2022年12月经上海交通大学医学院苏州九龙医院临床诊断为大脑中动脉血栓并行血管内机械取栓术的患者96例,其中渗出组67例,非渗出组29例,所有病例以7∶3的比例随机分为训练集(67例)与测试集(29例),应用ITK-SNAP软件对CT平扫图像进行感兴趣区域勾画,提取影像组学特征;使用Mann-Whitney U检验、Pearson相关与最小绝对收缩和选择算子进行特征筛选。在训练集与测试集使用随机森林与极限梯度提升进行建模,分别绘制受试者操作特征曲线,计算曲线下面积(AUC)、敏感度、特异度及最佳阈值,应用决策曲线分析评估所得到模型的临床应用价值。

结果

通过筛选得到6个最大预测效能影像组学特征,随机森林的训练模型具有最高的预测效能,该模型在训练集AUC值为0.997,95%CI:0.990~1.000,准确性、敏感度、特异度及最佳阈值分别为97.0%、97.8%、95.2%及0.700,决策曲线显示模型阈值在0.5~0.9的区间内具有较高的临床净收益。

结论

基于CT平扫的影像组学特征对大脑中动脉血栓患者机械取栓术后的造影剂外渗具有较高的预测价值。

Objective

To explore the application value of imaging omics based on non-contrast computed tomography (NCCT) in predicting extravasation of contrast agents during endovascular mechanical thrombectomy in patients with unilateral middle cerebral artery occlusion stroke.

Methods

A total of 96 patients with clinically diagnosed middle cerebral artery thrombosis and underwent endovascular mechanical thrombectomy in Suzhou kowloon Hospital, Shanghai Jiaotong University School of Medicine, were collected, including 67 patients in the exudative group and 29 patients in the non-exudative group. All patients were randomly assigned into a training set (67 cases) and a test set (29 cases) at a ratio of 7:3. The regions of interest of NCCT images were delineated using ITK-SNAP software to extract radiological characteristics. Mann-Whitney U test, Pearson correlation coefficient (Pearson), and the least absolute shrinkage and selection operator were used for feature selection. Models were trained and tested using Random Forest (RF) and Extreme Gradient Boosting (XGBoost). The ROC curves were plotted, and the area under the ROC curve (AUC), sensitivity, specificity, and optimal thresholds were calculated. The clinical utility of the models was further assessed through decision curve analysis (DCA).

Results

Through screening, we obtained 6 imaging radiomics features that have the greatest predictive power. The training model of RF demonstrated the highest predictive efficiency. The AUC value of the model in the training group was 0.997, 95%CI: 0.990-1.000, and the accuracy, sensitivity, specificity and optimal thresholds were 97.0%, 97.8%, 95.2%, and 0.700, respectively. The DCA curve showed that the model threshold had a high clinical net benefit across a broad range, specifically from 0.5 to 0.9.

Conclusion

Machine learning based on NCCT demonstrates a high predictive value for the extravasation detection of contrast media during embolectomy of the middle cerebral artery.

图1 大脑前循环梗死患者CT平扫图像分割、图像特征提取和筛选及模型构建流程图 注:NCCT为CT平扫,ROI为感兴趣区域;GLCM为灰度共生矩阵,GLRLM为灰度级长矩阵,GLSZM灰度级带矩阵,GLDM为灰度依赖性矩阵,Lasso分析为最小绝对收缩和选择算子分析,ROC为受试者操作特征曲线
表1 大脑前循环梗死患者训练集中外渗组与非外渗组基本临床资料比较
表2 大脑前循环梗死患者训练集及与测试集临床资料比较
图2 筛选得到的6个最大预测效能特征的权重图 注:feature_name为特征名称;wavelet:小波变换;HHL:表示图像用X方向的高通函数滤波、Y方向的高通函数滤波、Z方向的低通函数滤波;firstoder:一阶统计;interquartileRange:四分位数范围;LHH:表示图像用X方向的低通函数滤波、Y方向的高通函数滤波、Z方向的高通函数滤波;Skewness:偏度;glszm:灰度级带矩阵;GrayLevelNonUniformityNormalized:归一化灰度不均匀性;gldm:灰度依赖性矩阵;DependenceNonUniformityNormalized:归一化依赖不均匀性;LLH:表示图像用X方向的低通函数滤波、Y方向的低通函数滤波、Z方向的高通函数滤波;ZonePercentage:区域百分比;square:平方,即获取图像强度值的平方;SmallDependenceEmphasis:小依赖强调
表3 随机森林、XGBoost模型的训练集及测试集的诊断效能汇总
图3 基于CT平扫的影像组学特征预测急性大脑中动脉闭塞机械取栓术后造影剂外渗的随机森林模型训练集与测试集受试者操作特征分析曲线 注:Train为训练集;Test为测试集;AUC为曲线下面积
图4 基于CT平扫的影像组学特征预测急性大脑中动脉闭塞机械取栓术后造影剂外渗的随机森林训练集模型的决策曲线 注:Treat all表示所有造影剂外渗患者;Treat none表示所有造影剂未外渗患者
图5 基于CT平扫的影像组学特征预测急性大脑中动脉闭塞机械取栓术后造影剂外渗列线图 注:Radscore为影像组学评分;Procedure time为手术时长,Risk为风险概率,Total Points为总分,Points为评分
图6 基于CT平扫的影像组学特征预测急性大脑中动脉闭塞机械取栓术后造影剂外渗的列线图的校准曲线
21
Choi MH, Park GH, Lee JS, et al. Erythrocyte fraction within retrieved thrombi contributes to thrombolytic response in acute ischemic stroke [J]. Stroke, 2018, 49(3): 652-659.
22
Shin JW, Jeong HS, Kwon HJ, et al. High red blood cell composition in clots is associated with successful recanalization during intra-arterial thrombectomy [J]. PLoS One, 2018, 13(5): e0197492.
23
Hofmeister J, Bernava G, Rosi A, et al. Clot-based radiomics predict a mechanical thrombectomy strategy for successful recanalization in acute ischemic stroke [J]. Stroke, 2020, 51(8): 2488-2494.
24
Sarioglu O, Sarioglu FC, Capar AE, et al. Clot-based radiomics features predict first pass effect in acute ischemic stroke [J]. Interv Neuroradiol, 2022, 28(2): 160-168.
25
Van Voorst H, Bruggeman AAE, Yang W, et al. Thrombus radiomics in patients with anterior circulation acute ischemic stroke undergoing endovascular treatment [J]. J Neurointerv Surg, 2023, 15(e1): e79-e85.
26
Lummel N, Schulte-Altedorneburg G, Bernau C, et al. Hyperattenuated intracerebral lesions after mechanical recanalization in acute stroke [J]. AJNR Am J Neuroradiol, 2014, 35(2): 345-351.
27
Renú A, Amaro S, Laredo C, et al. Relevance of blood-brain barrier disruption after endovascular treatment of ischemic stroke: dual-energy computed tomographic study [J]. Stroke, 2015, 46(3): 673-679.
28
Aerts H, Velazquez ER, Leijenaar R, et al. Corrigendum: decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach [J]. Nat Commun, 2014, 5: 4006.
29
Song Y, Yin Z, Zhang C, et al. Random forest classifier improving phenylketonuria screening performance in two Chinese populations [J]. Front Mol Biosci, 2022, 9: 986556.
1
Warner JJ, Harrington RA, Sacco RL, et al. Guidelines for the early management of patients with acute ischemic stroke: 2019 update to the 2018 guidelines for the early management of acute ischemic stroke [J]. Stroke, 2019, 50(12): 3331-3332.
2
Powers WJ, Derdeyn CP, Biller J, et al. 2015 American Heart Association/American Stroke Association focused update of the 2013 guidelines for the early management of patients with acute ischemic stroke regarding endovascular treatment: a guideline for healthcare professionals from the American Heart Association/American Stroke Association [J]. Stroke, 2015, 46(10): 3020-3035.
3
Ohta H, Nakano S, Yokogami K, et al. Appearance of early venous filling during intra-arterial Reperfusion therapy for acute middle cerebral artery occlusion - a predictive sign for hemorrhagic complications [J]. Stroke, 2004, 35(4): 893-898.
4
Wang D, Liu J, Liu M, et al. Patterns of stroke between university hospitals and nonuniversity hospitals in mainland China: prospective multicenter hospital-based registry study [J]. World Neurosurg, 2017, 98: 258-265.
5
Chen Z, Zhang Y, Su Y, et al. Contrast extravasation is predictive of poor clinical outcomes in patients undergoing endovascular therapy for acute ischemic stroke in the anterior circulation [J]. J Stroke Cerebrovasc Dis, 2019, 29(1): 104494.
6
王艳, 李倩文, 郭道德, 等. CTP预测急性缺血性卒中患者脑动脉机械取栓术后对比剂外渗风险的初步研究 [J]. 医学影像学杂志, 2022, 32(7): 1085-1089.
7
Tang TY, Jiao Y, Cui Y, et al. Penumbra-based radiomics signature as prognostic biomarkers for thrombolysis of acute ischemic stroke patients: a multicenter cohort study [J]. J Neurol, 2020, 267(5): 1454-1463.
8
Chen X, Li Y, Zhou Y, et al. CT-based radiomics for differentiating intracranial contrast extravasation from intraparenchymal haemorrhage after mechanical thrombectomy [J]. Eur Radiol, 2022, 32(7): 4771-4779.
9
Ma Y, Wang J, Zhang H, et al. A CT-based radiomics nomogram for classification of intraparenchymal hyperdense areas in patients with acute ischemic stroke following mechanical thrombectomy treatment [J]. Front Neurosci, 2022, 16: 1061745.
10
Xu T, Wang Y, Yuan J, et al. Contrast extravasation and outcome of endovascular therapy in acute ischaemic stroke: a systematic review and meta-analysis [J]. BMJ Open, 2021, 11(7): e044917.
11
You SH, Kim B, Kim BK, et al. MR imaging for differentiating contrast staining from hemorrhagic transformation after endovascular thrombectomy in acute ischemic stroke: phantom and patient study [J]. AJNR Am J Neuroradiol, 2018, 39(12): 2313-2319.
12
霍礼功, 王钰, 陈蓓蕾, 等. 血脑屏障通透性定量评估及其在急性缺血性卒中患者中的应用 [J]. 国际脑血管病杂志, 2019, 27(4): 287-293.
13
Yedavalli V, Sammet S. Contrast extravasation versus hemorrhage after thrombectomy in patients with acute stroke [J]. J Neuroimaging, 2017, 27(6): 570-576.
14
Dekeyzer S, Nikoubashman O, Lutin B, et al. Distinction between contrast staining and hemorrhage after endovascular stroke treatment: one CT is not enough [J]. J Neurointerv Surg, 2017, 9(4): 394-398.
15
Bilgic AB, Gocmen R, Arsava EM, et al. The Effect of clot volume and permeability on response to intravenous tissue plasminogen activator in acute ischemic stroke [J]. J Stroke Cerebrovasc Dis, 2020, 29(2): 104541.
16
Dutra BG, Tolhuisen ML, Alves HCBR, et al. Thrombus imaging characteristics and outcomes in acute ischemic stroke patients undergoing endovascular treatment [J]. Stroke, 2019, 50(8): 2057-2064.
17
Shin JW, Jeong HS, Kwon HJ, et al. High red blood cell composition in clots is associated with successful recanalization during intra-arterial thrombectomy [J]. PLoS One, 2018, 13(5): e0197492.
18
Aliena-Valero A, Baixauli-Martín J, Torregrosa G, et al.Clot composition analysis as a diagnostic tool to gain insight into ischemic stroke etiology: a systematic review [J]. J Stroke, 2021, 23(3): 327-342.
19
Patel TR, Fricano S, Waqas M, et al. Increased perviousness on CT for acute ischemic stroke is associated with fibrin/platelet-rich clots [J]. AJNR Am J Neuroradiol, 2021, 42(1): 57-64.
20
Patel TR, Santo BA, Baig AA, et al. Histologically interpretable clot radiomic features predict treatment outcomes of mechanical thrombectomy for ischemic stroke [J]. Neuroradiology, 2023, 65(4): 737-749.
[1] 梁章荣, 梁伟伟, 周妙, 黄尚明, 雷俊娜, 刘亚丽, 李旷怡, 张英俭. 急性脑梗死并发吸入性肺炎的危险因素及预后分析[J/OL]. 中华肺部疾病杂志(电子版), 2024, 17(02): 268-271.
[2] 孙顗淼, 张颖. 糖尿病患者急性脑梗死取栓术后发生对比剂肾病的影响因素及预测模型建立[J/OL]. 中华肾病研究电子杂志, 2024, 13(04): 188-194.
[3] 谢井伟, 王森, 王非, 郭永坤. STA-MCA血管搭桥术治疗烟雾病[J/OL]. 中华神经创伤外科电子杂志, 2024, 10(05): 318-320.
[4] 李刚, 潘晓帆, 田雪, 刘路路. CT灌注成像参数及血栓弹力图对急性前循环脑梗死早期神经功能恶化的预测价值分析[J/OL]. 中华神经创伤外科电子杂志, 2024, 10(04): 226-232.
[5] 张艺, 任秀君, 郭孟玮, 赵雅芳, 李一凡, 李佳阳, 任晓暄, 邬继红, 卢海洋. 电针预处理对脑缺血再灌注大鼠行为学及外周血内皮祖细胞的影响[J/OL]. 中华神经创伤外科电子杂志, 2024, 10(02): 71-77.
[6] 初晨宇, 徐强, 饶军华, 李岳锋. 眶上锁孔入路手术建立食蟹猴大脑中动脉闭塞模型[J/OL]. 中华脑科疾病与康复杂志(电子版), 2024, 14(01): 8-13.
[7] 陈军, 许明伟. 经非责任动脉瘤侧翼点入路开颅一期夹闭双侧大脑中动脉动脉瘤[J/OL]. 中华脑科疾病与康复杂志(电子版), 2024, 14(01): 61-64.
[8] 赵倩, 刘文超, 李玺琳, 章邱东. 老年急性脑梗死诱发胃肠损伤的风险因素分析及模型构建[J/OL]. 中华消化病与影像杂志(电子版), 2024, 14(03): 213-217.
[9] 窦丽辉, 李鹏, 窦静敏, 王贵玲. 辨证针灸联合双歧杆菌三联活菌胶囊治疗脑梗死恢复期脾胃虚弱证功能性消化不良的疗效[J/OL]. 中华消化病与影像杂志(电子版), 2024, 14(03): 218-221.
[10] 梁铭垚, 袁健瑜, 关雨霏, 左思程, 阳新明, 陈巧燕. 多壳扩散磁共振成像在缺血性卒中模型的应用[J/OL]. 中华介入放射学电子杂志, 2024, 12(04): 362-368.
[11] 潘鑫, 黄晓云, 王超, 顾慧, 唐加波, 王鹏, 崔恒熙, 李政. 院前亚低温结合院内溶栓救治急性脑梗死的效果[J/OL]. 中华卫生应急电子杂志, 2024, 10(03): 145-148.
[12] 克地尔牙·马合木提, 胡波, 杨琼, 闫素, 胡岚卿, 高沛沛, 姚恩生. 依达拉奉右莰醇对急性脑梗死后认知功能障碍的疗效观察[J/OL]. 中华脑血管病杂志(电子版), 2024, 18(05): 459-466.
[13] 刘焕亮, 崔慧娟, 曹慧, 付源. 颈动脉狭窄处剪切率对高同型半胱氨酸血症患者脑梗死的预测价值[J/OL]. 中华脑血管病杂志(电子版), 2024, 18(04): 317-322.
[14] 刘晓梅, 罗永梅, 傅瑜. 基于信息化老年综合评估的多学科管理护理模式在脑梗死患者中的应用效果[J/OL]. 中华脑血管病杂志(电子版), 2024, 18(03): 255-264.
[15] 陈绚, 欧宁江, 叶洁梅, 邓瑾倩. 纤维蛋白原β链启动因子基因多态性与颈动脉粥样硬化斑块稳定性的关联性研究[J/OL]. 中华脑血管病杂志(电子版), 2024, 18(01): 33-39.
阅读次数
全文


摘要