Department of Electronic Engineering, Fudan University, Shanghai, China.
Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China.
J Clin Neurosci. 2023 Sep;115:101-107. doi: 10.1016/j.jocn.2023.07.025. Epub 2023 Aug 3.
Intracranial aneurysm is a severe cerebrovascular disease that can result in subarachnoid hemorrhage (SAH), leading to high incidence and mortality rates. Computer-aided detection of aneurysms can assist doctors in enhancing diagnostic accuracy. The analysis of aneurysm imaging holds considerable predictive value for aneurysm rupture. This paper presents a method for the detection of aneurysms and analysis of ruptures using digital subtraction angiography (DSA).
A total of 263 aneurysms were analyzed, with 125 being ruptured and 138 being unruptured. Firstly, a filter based on the eigenvalues of the Hessian matrix was proposed for aneurysm detection. The filter's detection parameters can be automatically obtained through Bayesian optimization. Aneurysms were detected based on their structure and the response of the filter. Secondly, considering the variations in blood flow and morphology among aneurysms in DSA, intensity, texture, and blood perfusion features were extracted from the ruptured aneurysms and unruptured aneurysms. Subsequently, a sparse representation (SR) method was utilized to classify unruptured and ruptured aneurysms.
The experimental results for aneurysm detection showed that the F1-score was 94.1%. In the classification of ruptured and unruptured aneurysms, the accuracy, sensitivity, specificity, and area under curve (AUC) were 96.1%, 94.4%, 97.5%, and 0.982, respectively.
This paper presents a scheme combining an aneurysm detection filter and machine learning, offering a reliable solution for the diagnosis and prediction of aneurysm rupture.
颅内动脉瘤是一种严重的脑血管疾病，可导致蛛网膜下腔出血（SAH），具有较高的发病率和死亡率。计算机辅助检测动脉瘤可以帮助医生提高诊断准确性。对动脉瘤成像的分析对动脉瘤破裂具有重要的预测价值。本文提出了一种基于数字减影血管造影（DSA）的动脉瘤检测和破裂分析方法。
共分析了 263 个动脉瘤，其中 125 个为破裂动脉瘤，138 个为未破裂动脉瘤。首先，提出了一种基于 Hessian 矩阵特征值的滤波器用于检测动脉瘤。该滤波器的检测参数可以通过贝叶斯优化自动获得。基于结构和滤波器的响应来检测动脉瘤。其次，考虑到 DSA 中动脉瘤的血流和形态变化，从破裂和未破裂的动脉瘤中提取了强度、纹理和血流灌注特征。然后，利用稀疏表示（SR）方法对未破裂和破裂的动脉瘤进行分类。
动脉瘤检测的实验结果表明，F1 得分为 94.1%。在破裂和未破裂动脉瘤的分类中，准确率、灵敏度、特异度和曲线下面积（AUC）分别为 96.1%、94.4%、97.5%和 0.982。
本文提出了一种结合动脉瘤检测滤波器和机器学习的方案，为动脉瘤破裂的诊断和预测提供了可靠的解决方案。
