面向主动脉缩窄辅助诊断的神经网络模型设计

doi:10.13190/j.jbupt.2021-185

北京邮电大学学报 ›› 2022, Vol. 45 ›› Issue (4): 1-6.doi: 10.13190/j.jbupt.2021-185

• 智慧医疗 • 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¹

1. 北京邮电大学北京先进信息网络实验室, 北京 100876;
2. 首都医科大学附属北京安贞医院小儿心脏中心, 北京 100029

收稿日期:2021-09-01 出版日期:2022-08-28 发布日期:2022-09-03
通讯作者: 罗涛(1971—),男,教授,博士生导师,邮箱:tluo@bupt.edu.cn。 E-mail:tluo@bupt.edu.cn
作者简介:武兴坤(1997—),男,硕士生。

Design of Neural Network Model for Auxiliary Diagnosis of Coarctation of Aorta

WU Xingkun¹, LUO Tao¹, LIU Aijun², YANG Ming², ZHANG Wenjing¹

1. Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing 100876, China;
2. Pediatric Heart Center, Beijing Anzhen Hospital Affiliated to the Capital Medical University, Beijing 100029, China

Received:2021-09-01 Online:2022-08-28 Published:2022-09-03

摘要/Abstract

摘要： 为了辅助临床医生更快、更准确地进行主动脉缩窄的术前评估，结合心脏计算机断层扫描图像的三维空间特征，提出一种基于三维卷积神经网络的主动脉缩窄辅助诊断模型。相比于传统主动脉缩窄辅助诊断方法，使用这种新模型可在提高诊断结果可靠性的同时，直接面向图像操作，无需进行繁杂的数据预处理，诊断准确率、查准率和查全率均有显著提高。

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: A model of coarctation of aorta based on three-dimensional aided diagnosis model of aortic coarctation based on three-dimensional convolution neural network is proposed, which combines the three-dimensional spatial features of cardiac computed tomography images. Compared with the traditional auxiliary diagnosis method of aortic coarctation, the proposed method not only improves the reliability of diagnosis results, but also directly processes images operation without complicated data preprocessing process. The performance in terms of diagnosis accuracy, precision and recall has been significantly improved.

Key words: coarctation of aorta, three-dimensional convolutional neural network, three-dimensional spatial features, cardiac computed tomography image

中图分类号:

TP183

武兴坤, 罗涛, 刘爱军, 杨明, 张文静. 面向主动脉缩窄辅助诊断的神经网络模型设计[J]. 北京邮电大学学报, 2022, 45(4): 1-6.

WU Xingkun, LUO Tao, LIU Aijun, YANG Ming, ZHANG Wenjing. Design of Neural Network Model for Auxiliary Diagnosis of Coarctation of Aorta[J]. Journal of Beijing University of Posts and Telecommunications, 2022, 45(4): 1-6.

参考文献

[1] TORO-SALAZAR O H, STEINBERGER J, THOMAS W, et al. Long-term follow-up of patients after coarctation of the aorta repair[J]. The American Journal of Cardiology, 2002, 89(5):541-547.
[2] NIE P, WANG X, CHENG Z, et al. The value of low-dose prospective ECG-gated dual-source CT angiography in the diagnosis of coarctation of the aorta in infants and children[J]. Clinical Radiology, 2012, 67(8):738-745.
[3] 邵江, 牟华明, 李俊. 128层螺旋CT冠状动脉成像在冠心病诊断中的应用价值[J]. 中国循证心血管医学杂志, 2014, 6(1):34-36. SHAO J, MOU H M, LI J. Application value of 128-slices spiral CT coronary artery imaging in diagnosis of coronary heart disease[J]. Chinese Journal of Evidence-Based Cardiovascular Medicine, 2014, 6(1):34-36.
[4] 胡喜红. 64排螺旋CT评价儿童先天性心脏病的方法学及应用研究[D]. 上海:复旦大学, 2009. HU X H. Methodology and clinical application of 64-detector computed tomography in diagnosing congenital heart disease in children[D]. Shanghai:Fudan University, 2009.
[5] 高海娟, 平子良. 医学超声远程现状与案例分析[J]. 现代电子技术, 2014, 37(20):137-140. GAO H J, PING Z L. Current situation and case study of medical tele-ultrasound[J]. Modern Electronics Technique, 2014, 37(20):137-140.
[6] VAN DEN OEVER L B, VONDER M, VAN ASSEN M, et al. Application of artificial intelligence in cardiac CT:from basics to clinical practice[J/OL]. European Journal of Radiology, 2020, 128:108969[2021-07-31]. https://www.sciencedirect.com/science/article/pii/S0720048X20301583.
[7] JUAN R, MUFTI M, MD M, et al. 3D DenseNet ensemble in 4-way classification of Alzheimer's disease[C]//International Conference on Brain Informatics. Berlin:Springer, 2020:85-96.
[8] TRAN D, BOURDEV L, FERGUS R, et al. Learning spatiotemporal features with 3D convolutional networks[C]//2015 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE Press, 2015:4489-4497.
[9] BAHADO-SINGH R, VISHWESWARAIAH S, SAYED N M, et al. 62:deep learning/artificial intelligence and the epigenomic prediction of coarctation of the aorta[J]. American Journal of Obstetrics and Gynecology, 2019, 220(1):50.
[10] 祝雨雷. 计算流体力学与机器学习在主动脉缩窄及主动脉瓣狭窄患者评估中的临床应用研究[D]. 广州:华南理工大学, 2018. ZHU Y L. The clinical application research of computational fluid dynamics and machine learning in evaluation of coarctation of aorta and aortic stenosis patients[D]. Guangzhou:South China University of Technology, 2018.
[11] 黄力宇, 杨茂青, 黄美萍, 等. 由CT影像确定主动脉缩窄处压力差的装置与方法:CN106803251A[P]. 2017-06-06.
[12] 曹鹏. 不均衡数据分类方法的研究[D]. 沈阳:东北大学, 2014. CAO P. The research of imbalanced data classification[D]. Shenyang:Northeastern University, 2014.
[13] 梁福来, 宋千, 张汉华, 等. 基于照度的SAR图像均衡算法研究[J]. 电子与信息学报, 2012, 34(10):2458-2465. LIANG F L, SONG Q, ZHANG H H, et al. Research on SAR image equalization algorithm based on illumination[J]. Journal of Electronics and Information Technology, 2012, 34(10):2458-2465.

面向主动脉缩窄辅助诊断的神经网络模型设计

Design of Neural Network Model for Auxiliary Diagnosis of Coarctation of Aorta

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价