• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Frontiers in Bioengineering and Biotechnology >Grade Prediction of Bleeding Volume in Cesarean Section of Patients With Pernicious Placenta Previa Based on Deep Learning
【24h】

Grade Prediction of Bleeding Volume in Cesarean Section of Patients With Pernicious Placenta Previa Based on Deep Learning

机译：基于深度学习的基于深度学习的胎盘术患者剖宫产段出血量的等级预测

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In order to predict the amount of bleeding in the cesarean section of the patients with pernicious placenta previa, and to provide the evidence for the formulation of hemostasis plan before the operation, this paper designs an automatic prediction method based on MRI uterus image. Firstly, the method uses the DeepLab-V3+ network to segment the original MRI abdominal image to obtain the uterine region image. Then, the uterine region image and the corresponding blood loss data are trained by VGGNet-16 network, and the classification model of blood loss level is obtained. The date show that the accuracy, sensitivity and specificity of the classification model are 75.61%, 73.75% and 77.46% respectively on 82 sets of positive and 128 sets of negative MRI images. The results show that this method has a potential clinical application in the prediction of the bleeding volume of cesarean section.
机译：为了预测PREVIA患者的剖宫产患者的出血量，并提供了在手术前制定止血计划的证据，本文设计了一种基于MRI子宫图像的自动预测方法。首先，该方法使用DEEPLAB-V3 +网络分割原始MRI腹部图像以获得子宫区域图像。然后，通过VGGNET-16网络训练子宫区域图像和相应的血液损失数据，并且获得损伤水平的分类模型。目前表明，分类模型的准确性，敏感性和特异性分别为82套阳性和128套负极MRI图像分别为75.61％，73.75％和77.46％。结果表明，该方法具有潜在的临床应用，以预测剖宫产的出血体积。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号