期刊
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
卷 208, 期 -, 页码 -出版社
ELSEVIER IRELAND LTD
DOI: 10.1016/j.cmpb.2021.106278
关键词
Ischemic stroke; Computed tomography; Image segmentation; Deep leaning; U-Net network
类别
资金
- Key Projects of Medical Science Research in Hebei Province [20191252]
This study developed a multi-scale U-Net deep network model for automatic image segmentation of acute ischemic stroke lesions on non-enhanced CT images, which showed higher accuracy and shorter processing time compared to the classic U-Net method.
Background and Objective: Acute ischemic stroke requires timely diagnosis and thrombolytic therapy, but it is difficult to locate and quantify the lesion site manually. The purpose of this study was to explore a more rapid and effective method for automatic image segmentation of acute ischemic stroke. Methods: The image features of 30 stroke patients were segmented from non-enhanced computed tomography (CT) images using a multi-scale U-Net deep network model. The Dice loss function training model was used to counter the similar imbalance problem in the data. The difference was compared between manual segmentation and automatic segmentation. Results: The Dice similarity coefficient based on multi-scale convolution U-Net network segmentation was 0.86 +/- 0.04, higher than the Dice based on classic U-Net (0.81 +/- 0.07, P = 0.001). The lesion contour of automatic segmentation based on multi-scale U-Net was very close to manual segmentation. The error of lesion area is 1.28 +/- 0.59 mm(2,) and the Pearson correlation coefficient was r = 0.986 (P < 0.01). The motion time of automatic segmentation is less than 20 ms. Conclusions: Multi-scale U-Net deep network model can effectively segment ischemic stroke lesions in non-enhanced CT and meet real-time clinical requirements. (C) 2021 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据