Department of Radiology, Beijing Chaoyang Hospital, Capital Medical University, China (X.Y., Y.L., H.L., P.S., X.L., X.J., Q.Y.).
Institute of Advanced Research, Infervision Medical Technology Co, Ltd, Beijing, China (P.Y., H.Z., R.Z.).
Stroke. 2023 May;54(5):1357-1366. doi: 10.1161/STROKEAHA.122.041520. Epub 2023 Mar 13.
Cerebral venous thrombosis (CVT) is a rare cerebrovascular disease. Routine brain magnetic resonance imaging is commonly used to diagnose CVT. This study aimed to develop and evaluate a novel deep learning (DL) algorithm for detecting CVT using routine brain magnetic resonance imaging.
Routine brain magnetic resonance imaging, including T1-weighted, T2-weighted, and fluid-attenuated inversion recovery images of patients suspected of CVT from April 2014 through December 2019 who were enrolled from a CVT registry, were collected. The images were divided into 2 data sets: a development set and a test set. Different DL algorithms were constructed in the development set using 5-fold cross-validation. Four radiologists with various levels of expertise independently read the images and performed diagnosis within the test set. The diagnostic performance on per-patient and per-segment diagnosis levels of the DL algorithms and radiologist's assessment were evaluated and compared.
A total of 392 patients, including 294 patients with CVT (37±14 years, 151 women) and 98 patients without CVT (42±15 years, 65 women), were enrolled. Of these, 100 patients (50 CVT and 50 non-CVT) were randomly assigned to the test set, and the other 292 patients comprised the development set. In the test set, the optimal DL algorithm (multisequence multitask deep learning algorithm) achieved an area under the curve of 0.96, with a sensitivity of 96% (48/50) and a specificity of 88% (44/50) on per-patient diagnosis level, as well as a sensitivity of 88% (129/146) and a specificity of 80% (521/654) on per-segment diagnosis level. Compared with 4 radiologists, multisequence multitask deep learning algorithm showed higher sensitivity both on per-patient (all <0.05) and per-segment diagnosis levels (all <0.001).
The CVT-detected DL algorithm herein improved diagnostic performance of routine brain magnetic resonance imaging, with high sensitivity and specificity, which provides a promising approach for detecting CVT.
脑静脉血栓形成（CVT）是一种罕见的脑血管疾病。常规脑部磁共振成像常用于诊断 CVT。本研究旨在开发和评估一种利用常规脑部磁共振成像检测 CVT 的新型深度学习（DL）算法。
收集 2014 年 4 月至 2019 年 12 月期间从 CVT 登记处招募的疑似 CVT 患者的常规脑部磁共振成像，包括 T1 加权、T2 加权和液体衰减反转恢复图像。这些图像被分为两个数据集：一个开发集和一个测试集。在开发集中，使用 5 折交叉验证构建了不同的 DL 算法。四位具有不同专业水平的放射科医生在测试集中独立阅读图像并进行诊断。评估和比较了 DL 算法和放射科医生评估在患者和每段诊断水平上的诊断性能。
共纳入 392 例患者，包括 294 例 CVT 患者（37±14 岁，151 例女性）和 98 例非 CVT 患者（42±15 岁，65 例女性）。其中，100 例患者（50 例 CVT 和 50 例非 CVT）被随机分配到测试集中，其余 292 例患者构成开发集。在测试集中，最佳的 DL 算法（多序列多任务深度学习算法）在患者水平上的曲线下面积为 0.96，其敏感性为 96%（48/50），特异性为 88%（44/50），在每段水平上的敏感性为 88%（129/146），特异性为 80%（521/654）。与 4 位放射科医生相比，多序列多任务深度学习算法在患者和每段诊断水平上均具有更高的敏感性（均<0.05）。
本文提出的 CVT 检测 DL 算法提高了常规脑部磁共振成像的诊断性能，具有较高的敏感性和特异性，为检测 CVT 提供了一种有前途的方法。
