Automatic segmentation of cerebral infarcts in follow-up computed tomography images with convolutional neural networks
Automatic segmentation of cerebral infarcts in follow-up computed tomography images with convolutional neural networks
复制标题
DOI：
10.1136/neurintsurg-2019-015471
复制
发表时间：
2020-09-01
影响因子：
4.8
通讯作者：
Marquering, Henk A.
中科院分区：
文献类型：
--
作者：
Barros, Renan Sales;Tolhuisen, Manon L.;Marquering, Henk A.
背景和目的脑CT容积是急性缺血性脑卒中治疗试验中有价值的预后指标，与功能预后密切相关。然而，其手动体积评估要求太高，无法在临床实践中实施。目的评价卷积神经网络（CNN）在大样本急性缺血性脑卒中患者CT图像梗死体积自动分割中的应用价值。材料与方法我们纳入了1026例急性缺血性卒中患者的CT图像。通过手动描绘生成梗死分割的参考标准。我们介绍了三种CNN模型，用于分割细微，中等和严重的低密度病变。全自动梗死分割被定义为这三个CNN结果的组合。将三CNN方法的结果与单个CNN方法的结果以及参考标准分割进行比较。结果中位梗死体积为48 mL（IQR 15-125 mL）。三CNN方法的体积与手动描绘的梗死体积之间的比较显示出极好的一致性，组内相关系数（ICC）为0.88。严重和中度低密度梗死的一致性更好，ICC分别为0.98和0.93。尽管在单一CNN方法中用于训练的患者数量要大得多，但三CNN方法的准确性大大优于单一CNN方法，后者的ICC为0.34。结论卷积神经网络对脑梗死体积的定量评估具有较高的准确性和应用价值，无论是对轻度还是重度低密度脑梗死。我们提出的三CNN方法大大优于更直接的单一CNN方法。
Background and purpose Infarct volume is a valuable outcome measure in treatment trials of acute ischemic stroke and is strongly associated with functional outcome. Its manual volumetric assessment is, however, too demanding to be implemented in clinical practice. Objective To assess the value of convolutional neural networks (CNNs) in the automatic segmentation of infarct volume in follow-up CT images in a large population of patients with acute ischemic stroke. Materials and methods We included CT images of 1026 patients from a large pooling of patients with acute ischemic stroke. A reference standard for the infarct segmentation was generated by manual delineation. We introduce three CNN models for the segmentation of subtle, intermediate, and severe hypodense lesions. The fully automated infarct segmentation was defined as the combination of the results of these three CNNs. The results of the three-CNNs approach were compared with the results from a single CNN approach and with the reference standard segmentations. Results The median infarct volume was 48 mL (IQR 15-125 mL). Comparison between the volumes of the three-CNNs approach and manually delineated infarct volumes showed excellent agreement, with an intraclass correlation coefficient (ICC) of 0.88. Even better agreement was found for severe and intermediate hypodense infarcts, with ICCs of 0.98 and 0.93, respectively. Although the number of patients used for training in the single CNN approach was much larger, the accuracy of the three-CNNs approach strongly outperformed the single CNN approach, which had an ICC of 0.34. Conclusion Convolutional neural networks are valuable and accurate in the quantitative assessment of infarct volumes, for both subtle and severe hypodense infarcts in follow-up CT images. Our proposed three-CNNs approach strongly outperforms a more straightforward single CNN approach.