北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2022, Vol. 45 ›› Issue (4): 1-6.

• 论文 •    下一篇

面向主动脉缩窄辅助诊断的神经网络模型设计

武兴坤1,罗涛1,刘爱军2,杨明2,张文静3,李剑峰1,李文秀2   

  1. 1. 北京邮电大学
    2. 北京安贞医院
    3.
  • 收稿日期:2021-09-01 修回日期:2021-10-28 出版日期:2022-08-28 发布日期:2022-06-26
  • 通讯作者: 罗涛 E-mail:tluo@bupt.edu.cn
  • 基金资助:
    国家自然科学基金

Design of Three-dimensional Convolution Neural Network Model for Intelligent Aided Diagnosis of Coarctation of Aorta

  • Received:2021-09-01 Revised:2021-10-28 Online:2022-08-28 Published:2022-06-26

摘要: 融合心脏CT图像的三维空间特征,提出一种基于三维卷积神经网络(3D Convolutional Neural Network,C3D)的主动脉缩窄(Coarctation of Aorta,CoA)辅助诊断模型3DCoA。相比于传统CoA 辅助诊断方法,3DCoA模型在提高诊断结果可靠性的同时,直接面向图像操作,无需繁杂的数据预处理过程。实验结果表明,3DCoA模型与现有方法相比,在诊断准确率、查准率和查全率方面的性能均得到显著改善。

关键词: 主动脉缩窄, 三维卷积神经网络, 三维空间特征, 心脏CT图像

Abstract: Combining the 3D spatial features of cardiac CT images, a model of coarctation of aorta (CoA) based on 3D convolutional neural network (C3D) is proposed (3DCoA). Compared with traditional CoA assisted diagnosis methods, 3DCoA model not only improves the reliability of diagnosis results, but also directly faces image operation without complicated data preprocessing process. The experimental results show that compared with the existing methods, the performance of 3DCoA model in diagnosis accuracy, precision and recall has been significantly improved.

Key words: coarctation of aorta, three-dimensional convolutional neural network, 3D spatial features, cardiac CT image

中图分类号: