Mah Yee-Haur, Nachev Parashkev, MacKinnon Andrew D
King's College Hospital NHS Foundation Trust, London, United Kingdom.
School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom.
Front Neurol. 2020 Jan 24;11:15. doi: 10.3389/fneur.2020.00015. eCollection 2020.
Acute stroke is often superimposed on chronic damage from previous cerebrovascular events. This background will inevitably modulate the impact of acute injury on clinical outcomes to an extent that will depend on the precise anatomical pattern of damage. Previous attempts to quantify such modulation have employed only reductive models that ignore anatomical detail. The combination of automated image processing, large-scale data, and machine learning now enables us to quantify the impact of this with high-dimensional multivariate models sensitive to individual variations in the detailed anatomical pattern. We introduce and validate a new automated chronic lesion segmentation routine for use with non-contrast CT brain scans, combining non-parametric outlier-detection score, Zeta, with an unsupervised 3-dimensional maximum-flow, minimum-cut algorithm. The routine was then applied to a dataset of 1,704 stroke patient scans, obtained at their presentation to a hyper-acute stroke unit (St George's Hospital, London, UK), and used to train a support vector machine (SVM) model to predict between low (0-2) and high (3-6) pre-admission and discharge modified Rankin Scale (mRS) scores, quantifying performance by the area under the receiver operating curve (AUROC). In this single center retrospective observational study, our SVM models were able to differentiate between low (0-2) and high (3-6) pre-admission and discharge mRS scores with an AUROC of 0.77 (95% confidence interval of 0.74-0.79), and 0.76 (0.74-0.78), respectively. The chronic lesion segmentation routine achieved a mean (standard deviation) sensitivity, specificity and Dice similarity coefficient of 0.746 (0.069), 0.999 (0.001), and 0.717 (0.091), respectively. We have demonstrated that machine learning models capable of capturing the high-dimensional features of chronic injuries are able to stratify patients-at the time of presentation-by pre-admission and discharge mRS scores. Our fully automated chronic stroke lesion segmentation routine simplifies this process, and utilizes routinely collected CT head scans, thereby facilitating future large-scale studies to develop supportive clinical decision tools.
急性中风常叠加于既往脑血管事件所致的慢性损伤之上。这种背景必然会在一定程度上调节急性损伤对临床结局的影响，其程度取决于损伤的精确解剖模式。以往量化这种调节作用的尝试仅采用了忽略解剖细节的简化模型。如今，自动化图像处理、大规模数据和机器学习的结合，使我们能够使用对详细解剖模式中的个体差异敏感的高维多元模型来量化其影响。我们引入并验证了一种用于非增强脑部CT扫描的新型自动化慢性病变分割程序，该程序将非参数异常值检测分数Zeta与无监督三维最大流最小割算法相结合。然后将该程序应用于1704例中风患者扫描数据集，这些扫描数据是在患者就诊于超急性中风单元（英国伦敦圣乔治医院）时获取的，并用于训练支持向量机（SVM）模型，以预测入院前和出院时改良Rankin量表（mRS）的低（0 - 2）分和高（3 - 6）分，通过受试者操作特征曲线下面积（AUROC）来量化性能。在这项单中心回顾性观察研究中，我们的SVM模型能够分别以0.77（95%置信区间为0.74 - 0.79）和0.76（0.74 - 0.78）的AUROC区分入院前和出院时mRS的低（0 - 2）分和高（3 - 6）分。慢性病变分割程序的平均（标准差）灵敏度、特异度和Dice相似系数分别为0.746（0.069）、0.999（0.001）和0.717（0.091）。我们已经证明，能够捕捉慢性损伤高维特征的机器学习模型能够在患者就诊时根据入院前和出院时的mRS分数对患者进行分层。我们的全自动慢性中风病变分割程序简化了这一过程，并利用常规收集的头部CT扫描，从而便于未来开展大规模研究以开发支持性临床决策工具。
