School of Electrical and Computer Engineering, University of Oklahoma, 101 David L Boren Blvd, Norman, OK, 73019, USA.
Department of Neurology, University of Oklahoma Medical Center, Oklahoma City, OK, USA.
Ann Biomed Eng. 2022 Apr;50(4):413-425. doi: 10.1007/s10439-022-02926-z. Epub 2022 Feb 2.
Accurately predicting clinical outcome of aneurysmal subarachnoid hemorrhage (aSAH) patients is difficult. The purpose of this study was to develop and test a new fully-automated computer-aided detection (CAD) scheme of brain computed tomography (CT) images to predict prognosis of aSAH patients. A retrospective dataset of 59 aSAH patients was assembled. Each patient had 2 sets of CT images acquired at admission and prior-to-discharge. CAD scheme was applied to segment intracranial brain regions into four subregions, namely, cerebrospinal fluid (CSF), white matter (WM), gray matter (GM), and leaked extraparenchymal blood (EPB), respectively. CAD then detects sulci and computes 9 image features related to 5 volumes of the segmented sulci, EPB, CSF, WM, and GM and 4 volumetrical ratios to sulci. Subsequently, applying a leave-one-case-out cross-validation method embedded with a principal component analysis (PCA) algorithm to generate optimal feature vector, 16 support vector machine (SVM) models were built using CT images acquired either at admission or prior-to-discharge to predict each of eight clinically relevant parameters commonly used to assess patients' prognosis. Finally, a receiver operating characteristics (ROC) method was used to evaluate SVM model performance. Areas under ROC curves of 16 SVM models range from 0.62 ± 0.07 to 0.86 ± 0.07. In general, SVM models trained using CT images acquired at admission yielded higher accuracy to predict short-term clinical outcomes, while SVM models trained using CT images acquired prior-to-discharge demonstrated higher accuracy in predicting long-term clinical outcomes. This study demonstrates feasibility to predict prognosis of aSAH patients using new quantitative image markers generated by SVM models.
准确预测颅内动脉瘤性蛛网膜下腔出血（aSAH）患者的临床预后较为困难。本研究旨在开发和测试一种新的全自动计算机辅助检测（CAD）方案，用于预测 aSAH 患者的预后。本研究收集了 59 例 aSAH 患者的回顾性数据集，每位患者均有 2 组入院时和出院前的脑部 CT 图像。CAD 方案用于将颅内脑区分割为 4 个亚区，即脑脊液（CSF）、白质（WM）、灰质（GM）和漏出性脑外血（EPB）。CAD 随后检测脑沟，并计算与分割脑沟、EPB、CSF、WM 和 GM 相关的 9 个图像特征以及 4 个容积比。随后，应用一种嵌入主成分分析（PCA）算法的留一病例交叉验证方法，生成最佳特征向量，使用入院时或出院前采集的 CT 图像，构建 16 个支持向量机（SVM）模型，用于预测 8 个常用评估患者预后的临床相关参数中的每一个。最后，使用受试者工作特征（ROC）方法评估 SVM 模型性能。16 个 SVM 模型的 ROC 曲线下面积范围为 0.62±0.07 至 0.86±0.07。总体而言，使用入院时 CT 图像训练的 SVM 模型对预测短期临床结局的准确性更高，而使用出院前 CT 图像训练的 SVM 模型在预测长期临床结局方面的准确性更高。本研究证明了使用 SVM 模型生成的新的定量图像标志物预测 aSAH 患者预后的可行性。
