深度学习自动分割多中心MRI急性缺血性脑卒中病灶
本研究评估深度学习算法在多中心异质性临床弥散加权MRI数据上分割急性缺血性病灶的能力,并探索其用于缺血性脑卒中表型分析的作用。算法由3个三维卷积神经网络集成构成,分别用单中心267例、MRI-GENIE 267例及两者混合数据训练,在MRI-GENIE 383例子集上与人工勾画比较。混合集成表现最佳,自动与人工病灶体积相关性极好(ρ=0.92;P<0.0001)。
要点
- 深度学习集成可准确分割多中心DWI急性缺血病灶,与人工勾画高度相关
- 小动脉闭塞型卒中病灶体积更小且分布不同
- 病灶体积与分布可用于大样本卒中表型分析
核心结论
- 用多中心多样数据训练的深度学习算法可自动准确分割临床DWI急性缺血病灶。
- 病灶体积与分布在大样本异质性多中心影像表型数据中可提供卒中亚型信息。
研究设计与样本
- 回顾性分析MRI-GENIE库中12个国际遗传研究中心的多中心临床DWI数据。
- 分割算法为3个三维卷积神经网络集成,分别用单中心267例、MRI-GENIE 267例及两者混合训练。
- 在MRI-GENIE另383例子集上与人工勾画比较,并对2770例做回归与地形分析。
主要发现
- 混合MRI-GENIE与单中心网络的集成表现最佳。
- 383例中自动与人工病灶体积相关性极好(ρ=0.92;P<0.0001)。
- 2770例DWI病灶体积中位数3.7 cm3(四分位距0.9-16.6 cm3)。
- 小动脉闭塞型卒中病灶体积更小(P<0.0001)且地形与其他亚型不同。
关键数值与推荐
- 自动与人工病灶体积比较:ρ=0.92;P<0.0001(383例)。
- 2770例DWI病灶体积中位数3.7 cm3,四分位距0.9-16.6 cm3。
- 小动脉闭塞型与其他亚型病灶体积比较:P<0.0001。
临床怎么用
- 可用于多中心临床DWI数据的自动病灶分割与体积、地形表型提取。
- 在大样本异质性影像数据中辅助卒中亚型研究与表型分析。
局限性
- 摘要未报告算法在前瞻性或其他队列中的外部验证结果。
- 摘要未报告分割精度的逐病灶一致性指标(如Dice)及失败病例情况。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
Background and Purpose- We evaluated deep learning algorithms' segmentation of acute ischemic lesions on heterogeneous multi-center clinical diffusion-weighted magnetic resonance imaging (MRI) data sets and explored the potential role of this tool for phenotyping acute ischemic stroke. Methods- Ischemic stroke data sets from the MRI-GENIE (MRI-Genetics Interface Exploration) repository consisting of 12 international genetic research centers were retrospectively analyzed using an automated deep learning segmentation algorithm consisting of an ensemble of 3-dimensional convolutional neural networks. Three ensembles were trained using data from the following: (1) 267 patients from an independent single-center cohort, (2) 267 patients from MRI-GENIE, and (3) mixture of (1) and (2). The algorithms' performances were compared against manual outlines from a separate 383 patient subset from MRI-GENIE. Univariable and multivariable logistic regression with respect to demographics, stroke subtypes, and vascular risk factors were performed to identify phenotypes associated with large acute diffusion-weighted MRI volumes and greater stroke severity in 2770 MRI-GENIE patients. Stroke topography was investigated. Results- The ensemble consisting of a mixture of MRI-GENIE and single-center convolutional neural networks performed best. Subset analysis comparing automated and manual lesion volumes in 383 patients found excellent correlation (ρ=0.92; P<0.0001). Median (interquartile range) diffusion-weighted MRI lesion volumes from 2770 patients were 3.7 cm3 (0.9-16.6 cm3). Patients with small artery occlusion stroke subtype had smaller lesion volumes ( P<0.0001) and different topography compared with other stroke subtypes. Conclusions- Automated accurate clinical diffusion-weighted MRI lesion segmentation using deep learning algorithms trained with multi-center and diverse data is feasible. Both lesion volume and topography can provide insight into stroke subtypes with sufficient sample size from big heterogeneous multi-center clinical imaging phenotype data sets.
引用
- Wu O, Winzeck S, Giese AK, et al. Big Data Approaches to Phenotyping Acute Ischemic Stroke Using Automated Lesion Segmentation of Multi-Center Magnetic Resonance Imaging Data. Stroke. 2019. PMID: 31177973. doi:10.1161/STROKEAHA.119.025373
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。