脑卒中患者转院接受血管内治疗时重复显像的价值

脑卒中患者转院接受血管内治疗时重复显像的价值

劳拉·C·范·米宁1号，内利亚·阿拉特·泰瑞罗斯23号，阿德里安·E·格罗特1号，马农·卡佩尔霍夫3号，卢多·F·M·比宁3号，亨克·A·马克林23号，巴特·J·埃默3号，伊沃·B·W·E·M·鲁斯1号，查尔斯·B·L·M·马约伊3号，乔纳森·M·库蒂尼奥4号

从属关系

PMID:33685983 DOI:10.1136/neurintsurg-2020-017050

摘要

背景：被转移到综合性卒中中心进行血管内治疗（EVT）的卒中患者在EVT前经常进行重复的神经影像学检查。

目的：评价重复成像的成功率及其对治疗次数的影响。

方法：我们纳入了2016-2019年由主要卒中中心转诊到我院进行EVT的大血管闭塞（LVO）卒中成年患者。我们排除了那些因为一次成像不可用、不完整或质量不高而重复成像的患者。结果包括治疗时间和重复的影像学表现。

结果：在677例转移性LVO卒中中，551例被纳入。在165/551例（30%）患者中重复成像，主要是因为临床改善（86/165（52%）或恶化（40/165（24%）。重复显像的患者门到腹股沟的时间比未重复显像的患者高（中位数43 vs 27 min，校正时差：20 min，95%可信区间15~25）。在因临床症状改善而重复造影的患者中，50/86（58%）的LVO已消退。在临床病情恶化的患者中，重复成像导致3/40（8%）患者无法进行EVT。无症状性颅内出血。最终，75/165（45%）的重复成像患者接受了EVT，而326/386（84%）的无重复成像患者接受了EVT（p<0.01）。

结论：30%的LVO卒中患者重复进行神经影像学检查，导致中位治疗延迟20分钟。在临床病情恶化的患者中，没有检测到sICH，重复成像很少改变EVT的适应证。然而，在超过一半的临床改善患者中，LVO已经消失，导致EVT的放弃。

关键词：CT；脑卒中；血栓切除术。

Background: Predictive maps of the final infarct may help therapeutic decisions in acute ischemic stroke patients. Our objectives were to assess whether integrating the reperfusion status into deep learning models would improve their performance, and to compare them to current clinical prediction methods.

Methods: We trained and tested convolutional neural networks (CNNs) to predict the final infarct in acute ischemic stroke patients treated by thrombectomy in our center. When training the CNNs, non-reperfused patients from a non-thrombectomized cohort were added to the training set to increase the size of this group. Baseline diffusion and perfusion-weighted magnetic resonance imaging (MRI) were used as inputs, and the lesion segmented on day-6 MRI served as the ground truth for the final infarct. The cohort was dichotomized into two subsets, reperfused and non-reperfused patients, from which reperfusion status specific CNNs were developed and compared to one another, and to the clinically-used perfusion-diffusion mismatch model. Evaluation metrics included the Dice similarity coefficient (DSC), precision, recall, volumetric similarity, Hausdorff distance and area-under-the-curve (AUC).

Results: We analyzed 109 patients, including 35 without reperfusion. The highest DSC were achieved in both reperfused and non-reperfused patients (DSC = 0.44 ± 0.25 and 0.47 ± 0.17, respectively) when using the corresponding reperfusion status-specific CNN. CNN-based models achieved higher DSC and AUC values compared to those of perfusion-diffusion mismatch models (reperfused patients: AUC = 0.87 ± 0.13 vs 0.79 ± 0.17, P < 0.001; non-reperfused patients: AUC = 0.81 ± 0.13 vs 0.73 ± 0.14, P < 0.01, in CNN vs perfusion-diffusion mismatch models, respectively).

Conclusion: The performance of deep learning models improved when the reperfusion status was incorporated in their training. CNN-based models outperformed the clinically-used perfusion-diffusion mismatch model. Comparing the predicted infarct in case of successful vs failed reperfusion may help in estimating the treatment effect and guiding therapeutic decisions in selected patients.