We implemented a deep learning (DL) algorithm for the 3-dimensional segmentation of perivascular spaces (PVSs) in deep white matter (DWM) and basal ganglia (BG). This algorithm is based on an autoencoder and a U-shaped network (U-net), and was trained and tested using T1-weighted magnetic resonance imaging (MRI) data from a large database of 1,832 healthy young adults. An important feature of this approach is the ability to learn from relatively sparse data, which gives the present algorithm a major advantage over other DL algorithms. Here, we trained the algorithm with 40 T1-weighted MRI datasets in which all “visible” PVSs were manually annotated by an experienced operator. After learning, performance was assessed using another set of 10 MRI scans from the same database in which PVSs were also traced by the same operator and were checked by consensus with another experienced operator. The Sorensen-Dice coefficients for PVS voxel detection in DWM (resp. BG) were 0.51 (resp. 0.66), and 0.64 (resp. 0.71) for PVS cluster detection (volume threshold of 0.5 within a range of 0 to 1). Dice values above 0.90 could be reached for detecting PVSs larger than 10 mm3 and 0.95 for PVSs larger than 15 mm3. We then applied the trained algorithm to the rest of the database (1,782 individuals). The individual PVS load provided by the algorithm showed a high agreement with a semi-quantitative visual rating done by an independent expert rater, both for DWM and for BG. Finally, we applied the trained algorithm to an age-matched sample from another MRI database acquired using a different scanner. We obtained a very similar distribution of PVS load, demonstrating the interoperability of this algorithm.

中文翻译：

---

使用卷积自动编码器和 U 形神经网络对 T1 加权 3 Tesla MR 图像上的血管周围空间进行 3D 分割


我们实施了一种深度学习 (DL) 算法，用于对深部白质 (DWM) 和基底神经节 (BG) 中的血管周围空间 (PVS) 进行 3 维分割。该算法基于自动编码器和 U 形网络 (U-net)，并使用来自 1,832 名健康年轻人的大型数据库的 T1 加权磁共振成像 (MRI) 数据进行训练和测试。这种方法的一个重要特征是能够从相对稀疏的数据中学习，这使得本算法比其他深度学习算法具有主要优势。在这里，我们使用 40 个 T1 加权 MRI 数据集训练算法，其中所有“可见”PVS 均由经验丰富的操作员手动注释。学习后，使用来自同一数据库的另一组 10 次 MRI 扫描来评估性能，其中 PVS 也由同一操作员追踪，并与另一位经验丰富的操作员协商一致进行检查。 DWM 中 PVS 体素检测的 Sorensen-Dice 系数（分别为 BG）为 0.51（分别为 0.66），PVS 簇检测的 Sorensen-Dice 系数为 0.64（分别为 0.71）（0 到 1 范围内的体积阈值为 0.5）。对于检测大于 10 mm3 的 PVS，骰子值可以达到 0.90 以上；对于大于 15 mm3 的 PVS，骰子值可以达到 0.95。然后，我们将经过训练的算法应用于数据库的其余部分（1,782 人）。该算法提供的单独 PVS 负载与独立专家评级员针对 DWM 和 BG 进行的半定量视觉评级高度一致。最后，我们将经过训练的算法应用于使用不同扫描仪获取的另一个 MRI 数据库中的年龄匹配样本。我们获得了非常相似的 PVS 负载分布，证明了该算法的互操作性。