Gibson Erin, Ramirez Joel, Woods Lauren Abby, Ottoy Julie, Berberian Stephanie, Scott Christopher J M, Yhap Vanessa, Gao Fuqiang, Coello Roberto Duarte, Valdes Hernandez Maria, Lang Anthony E, Tartaglia Carmela M, Kumar Sanjeev, Binns Malcolm A, Bartha Robert, Symons Sean, Swartz Richard H, Masellis Mario, Singh Navneet, Moody Alan, MacIntosh Bradley J, Wardlaw Joanna M, Black Sandra E, Lim Andrew S P, Goubran Maged
SEB Centre for Brain Resilience & Recovery, Hurvitz Brain Sciences Program, Sunnybrook Research Institute, Toronto, Canada.
Centre for Clinical Brain Sciences, Department of Neuroimaging Sciences, University of Edinburgh, Edinburgh, UK.
Hum Brain Mapp. 2024 Dec 15;45(18):e70104. doi: 10.1002/hbm.70104.
White matter hyperintensities (WMH) of presumed vascular origin are a magnetic resonance imaging (MRI)-based biomarker of cerebral small vessel disease (CSVD). WMH are associated with cognitive decline and increased risk of stroke and dementia, and are commonly observed in aging, vascular cognitive impairment, and neurodegenerative diseases. The reliable and rapid measurement of WMH in large-scale multisite clinical studies with heterogeneous patient populations remains challenging, where the diversity of imaging characteristics across studies adds additional complexity to this task. We present segcsvd, a convolutional neural network-based tool developed to provide reliable and accurate WMH quantification across diverse clinical datasets. segcsvd was developed using a large dataset consisting of over 700 fluid-attenuated inversion recovery MRI scans from seven multisite studies, spanning a wide range of clinical populations, WMH burdens, and imaging protocols. Model training incorporated anatomical information through a novel hierarchical segmentation approach, together with extensive data augmentation techniques to improve performance across varied imaging conditions. Benchmarked against three widely available segmentation tools, segcsvd demonstrated superior accuracy, achieving mean Dice score improvements of 7.8% ± 9.7% over HyperMapp3r, 21.8% ± 8.6% over SAMSEG, and 43.5% ± 7.1% over WMH-SynthSeg across four diverse test datasets. segcsvd also maintained consistently high Dice scores across these test datasets (mean DSC = 0.86 ± 0.08), and exhibited strong, stable correlations with periventricular, deep, and total WMH ground truth volumes (mean r = 0.99 ± 0.01). Additionally, segcsvd was robust to low and moderate levels of simulated MRI spike noise artifacts and maintained strong performance across a range of binary segmentation thresholds and WMH burden levels. These findings suggest that segcsvd may provide more accurate and robust WMH segmentation performance for heterogeneous clinical datasets characterized by varying degrees of CSVD severity.
推测为血管源性的脑白质高信号（WMH）是基于磁共振成像（MRI）的脑小血管疾病（CSVD）生物标志物。WMH与认知功能下降、中风和痴呆风险增加相关，且常见于衰老、血管性认知障碍和神经退行性疾病中。在具有异质性患者群体的大规模多中心临床研究中，可靠且快速地测量WMH仍然具有挑战性，因为各研究中成像特征的多样性给这项任务增加了额外的复杂性。我们展示了segcsvd，这是一种基于卷积神经网络开发的工具，旨在为不同的临床数据集提供可靠且准确的WMH定量分析。segcsvd是使用一个大型数据集开发的，该数据集包含来自7项多中心研究的700多次液体衰减反转恢复MRI扫描，涵盖了广泛的临床人群、WMH负荷和成像协议。模型训练通过一种新颖的分层分割方法纳入解剖学信息，并结合广泛的数据增强技术来提高在各种成像条件下的性能。与三种广泛使用的分割工具进行基准测试时，segcsvd表现出卓越的准确性，在四个不同的测试数据集上，其平均骰子系数得分比HyperMapp3r提高了7.8%±9.7%，比SAMSEG提高了21.8%±8.6%，比WMH-SynthSeg提高了43.5%±7.1%。segcsvd在这些测试数据集中也始终保持较高的骰子系数得分（平均DSC = 0.86±0.08），并且与脑室周围、深部和总的WMH真实体积表现出强而稳定的相关性（平均r = 0.99±0.01）。此外，segcsvd对低水平和中等水平的模拟MRI尖峰噪声伪影具有鲁棒性，并且在一系列二元分割阈值和WMH负荷水平上都保持了强大的性能。这些发现表明，对于以不同程度的CSVD严重程度为特征的异质性临床数据集，segcsvd可能提供更准确、更稳健的WMH分割性能。
