Key Laboratory of Biomechanics and Mechanobiology, Ministry of Education, Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, China.
BioMind Technology AI Center, China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijng, China.
Hum Brain Mapp. 2022 Feb 15;43(3):929-939. doi: 10.1002/hbm.25695. Epub 2021 Oct 27.
White matter hyperintensities (WMHs) represent the most common neuroimaging marker of cerebral small vessel disease (CSVD). The volume and location of WMHs are important clinical measures. We present a pipeline using deep fully convolutional network and ensemble models, combining U-Net, SE-Net, and multi-scale features, to automatically segment WMHs and estimate their volumes and locations. We evaluated our method in two datasets: a clinical routine dataset comprising 60 patients (selected from Chinese National Stroke Registry, CNSR) and a research dataset composed of 60 patients (selected from MICCAI WMH Challenge, MWC). The performance of our pipeline was compared with four freely available methods: LGA, LPA, UBO detector, and U-Net, in terms of a variety of metrics. Additionally, to access the model generalization ability, another research dataset comprising 40 patients (from Older Australian Twins Study and Sydney Memory and Aging Study, OSM), was selected and tested. The pipeline achieved the best performance in both research dataset and the clinical routine dataset with DSC being significantly higher than other methods (p < .001), reaching .833 and .783, respectively. The results of model generalization ability showed that the model trained on the research dataset (DSC = 0.736) performed higher than that trained on the clinical dataset (DSC = 0.622). Our method outperformed widely used pipelines in WMHs segmentation. This system could generate both image and text outputs for whole brain, lobar and anatomical automatic labeling WMHs. Additionally, software and models of our method are made publicly available at https://www.nitrc.org/projects/what_v1.
脑白质高信号（WMHs）是脑小血管病（CSVD）最常见的神经影像学标志物。WMHs 的体积和位置是重要的临床指标。我们提出了一个使用深度全卷积网络和集成模型的管道，结合 U-Net、SE-Net 和多尺度特征，自动分割 WMHs 并估计其体积和位置。我们在两个数据集上评估了我们的方法：一个包含 60 名患者的临床常规数据集（从中国国家卒中登记处（CNSR）中选择）和一个由 60 名患者组成的研究数据集（从 MICCAI WMH 挑战赛（MWC）中选择）。我们的管道的性能与四种免费提供的方法进行了比较：LGA、LPA、UBO 检测器和 U-Net，从多种指标来看。此外，为了评估模型的泛化能力，还选择并测试了另一个包含 40 名患者的研究数据集（来自澳大利亚老年双胞胎研究和悉尼记忆和衰老研究（OSM））。该管道在研究数据集和临床常规数据集中的表现最佳，其 DSC 明显高于其他方法（p <.001），分别为.833 和.783。模型泛化能力的结果表明，在研究数据集上训练的模型（DSC = 0.736）比在临床数据集上训练的模型（DSC = 0.622）表现更好。我们的方法在 WMHs 分割方面优于广泛使用的管道。该系统可以为整个大脑、叶和解剖学的自动标注 WMHs 生成图像和文本输出。此外，我们的方法的软件和模型已在 https://www.nitrc.org/projects/what_v1. 上公开提供。
