Assessment of intracranial arterial collateralisation and venous microperfusion profile to predict infarct evolution in patients with early ischemic stroke and endovascular treatment using machine learning models

急性缺血性中风（AIS）的定义是由于供血血管闭塞和随后的依赖脑组织缺氧而导致流向大脑的血液中断。所有AIS的治疗方法都是通过溶解或移除阻塞脑部血流的血块来恢复脑部血流。静脉溶栓（tPA）治疗AIS已超过二十年。最近，一种称为血栓切除术的微创手术已被用于有效地清除大脑动脉中的血块。为了评估治疗方案，需要通过计算机断层扫描或磁共振成像检查脑组织及其血液循环。在医学影像上，有大量可修复组织的患者通常显示独特的血管，称为颅内侧支（IC）。在AIS期间，IC指的是一个辅助的血管通道网络，强大的IC可以暂时保持血液流向严重低灌注的脑区域，从而对组织灌注质量产生关键影响。因此，组织灌注是由动脉血液流入脑组织和流出到脑静脉所控制的。近年来，大多数研究都集中在该导管的动脉部分，但对其引流静脉部分知之甚少。有人提出，测定AIS患者微血管系统静脉部分的血流量，可以更好地反映脑组织灌注的整体质量，因为它反映的是通过脑组织后的血流量。静脉微血管灌注状态的医学影像学评估是非常必要的，因为它掌握了AIS期间大脑病理生理的重要信息，可以作为治疗决策和患者临床结果的重要生物标志物。另一个关键但尚未解决的问题是，不同的医疗方法是否会对静脉微循环的稳健性和治疗结果产生显著影响。我们在斯坦福大学（美国）和汉堡-埃彭多夫大学医学中心（德国）之间建立了强有力的国际合作，并建立了目前650名接受tPA和取栓治疗的AIS患者的最大的前瞻性数据库之一。我们建议在取栓治疗前使用多参数CT和MRI研究AIS患者的微血管灌注情况，重点关注静脉流出微循环。我们的目的是确定强健的皮质静脉微循环是否受到静脉溶栓的影响，以及这个参数是否会影响患者的预后。我们的研究结果将增加对AIS期间脑微血管病理生理的理解，我们努力为更好的个体化治疗选择和改进的医疗护理做出贡献，以优化脑卒中患者的临床结果。

Acute ischemic stroke (AIS) is defined as disruption of blood flow to the brain caused by an occlusion of a supplying vessel and subsequent oxygen deficiency of the dependent brain tissue. All AIS treatments seek to restore blood flow to the brain by dissolving or removing the clot blocking blood flow to the brain. Intravenous thrombolysis (tPA) has been the predominant treatment of AIS for over two decades. More recently, a minimally-invasive surgery called thrombectomy has been used to effectively remove the blood clot from the artery in the brain. In order to evaluate treatment options, the brain tissue and its blood circulation need to be examined by means of computer tomography or magnetic resonance imaging. On medical imaging, patients with a large amount of salvageable tissue usually show distinctive vessels called intracranial collaterals (IC). During AIS, IC refer to a subsidiary network of vascular channels and robust IC may temporarily preserve blood flow to otherwise critically hypoperfused brain areas thus pivotally effecting the quality of tissue perfusion. Consequently, tissue perfusion is governed by the in-flow of arterial blood to the brain tissue and its outflow into the cerebral veins. In recent years, most studies have focused on the arterial component of this conduit, but very little is known about the draining venous side of it. It has been proposed that determining the blood flow within the venous part of the microvascular system of AIS patients may even better reflect the overall quality of brain tissue perfusion, as it reflects blood flow after passing the brain tissue. It would be highly desirable to properly assess the venous microvascular perfusion status with medical imaging, as it holds crucial information about brain’s pathophysiology during AIS and may serve as an important biomarker for treatment decision making and patients’ clinical outcome. Another critical, yet unresolved question is, whether distinct medical treatment approaches would have notable effects on the robustness of venous microcirculation and treatment outcome. We have established a strong international collaboration between Stanford University (USA) and the University Medical Center Hamburg-Eppendorf (Germany) and generated one of the largest prospectively maintained databases of currently 650 AIS patients treated with tPA and thrombectomy. We propose to investigate the microvascular perfusion profile in AIS patients with a focus on venous out-flow microcirculation using multi-parametric CT and MRI prior to thrombectomy treatment. We aim to determine whether robust cortical venous microcirculation is influenced by intravenous thrombolysis and whether this parameter influences patient outcome. Our results will augment the understanding of cerebral microvascular pathophysiology during AIS and we strive to contribute to a better individual treatment selection and improved medical care to optimize clinical outcome for stroke patients.