Department of Neuroradiology, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Switzerland.
Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of Zurich, Switzerland.
Neuroradiol J. 2020 Aug;33(4):311-317. doi: 10.1177/1971400920937647. Epub 2020 Jul 7.
Digital subtraction angiography is the gold standard for detecting and characterising aneurysms. Here, we assess the feasibility of commercial-grade deep learning software for the detection of intracranial aneurysms on whole-brain anteroposterior and lateral 2D digital subtraction angiography images.
Seven hundred and six digital subtraction angiography images were included from a cohort of 240 patients (157 female, mean age 59 years, range 20-92; 83 male, mean age 55 years, range 19-83). Three hundred and thirty-five (47%) single frame anteroposterior and lateral images of a digital subtraction angiography series of 187 aneurysms (41 ruptured, 146 unruptured; average size 7±5.3 mm, range 1-5 mm; total 372 depicted aneurysms) and 371 (53%) aneurysm-negative study images were retrospectively analysed regarding the presence of intracranial aneurysms. The 2D data was split into testing and training sets in a ratio of 4:1 with 3D rotational digital subtraction angiography as gold standard. Supervised deep learning was performed using commercial-grade machine learning software (Cognex, ViDi Suite 2.0). Monte Carlo cross validation was performed.
Intracranial aneurysms were detected with a sensitivity of 79%, a specificity of 79%, a precision of 0.75, a F1 score of 0.77, and a mean area-under-the-curve of 0.76 (range 0.68-0.86) after Monte Carlo cross-validation, run 45 times.
The commercial-grade deep learning software allows for detection of intracranial aneurysms on whole-brain, 2D anteroposterior and lateral digital subtraction angiography images, with results being comparable to more specifically engineered deep learning techniques.
数字减影血管造影是检测和表征动脉瘤的金标准。在此，我们评估商用级深度学习软件在全脑前后位和侧位 2D 数字减影血管造影图像上检测颅内动脉瘤的可行性。
从 240 例患者的队列中纳入了 706 张数字减影血管造影图像（157 例女性，平均年龄 59 岁，范围 20-92；83 例男性，平均年龄 55 岁，范围 19-83）。187 个动脉瘤（41 个破裂，146 个未破裂；平均大小 7±5.3mm，范围 1-5mm；共 372 个显示动脉瘤）的数字减影血管造影系列中的 335 张（47%）单帧前后位和侧位图像和 371 张（53%）无动脉瘤的研究图像回顾性分析了颅内动脉瘤的存在情况。2D 数据以 4:1 的比例分为测试集和训练集，以 3D 旋转数字减影血管造影作为金标准。使用商用级机器学习软件（Cognex，ViDi Suite 2.0）进行监督深度学习。进行了蒙特卡罗交叉验证。
经过 45 次蒙特卡罗交叉验证，颅内动脉瘤的检测灵敏度为 79%，特异性为 79%，精度为 0.75，F1 评分为 0.77，曲线下面积均值为 0.76（范围 0.68-0.86）。
商用级深度学习软件可用于检测全脑、2D 前后位和侧位数字减影血管造影图像上的颅内动脉瘤，其结果与更专门设计的深度学习技术相当。
