基于两阶段全卷积神经网络的冠状动脉分割研究
A Study of Coronary Artery Segmentation Based on Two-Stage Fully Convolutional Neural Networks
DOI: 10.12677/CSA.2022.124084, PDF,  被引量   
作者: 吴春彪：广东工业大学，计算机学院，广东 广州
关键词: 冠状动脉；全卷积神经网络；两阶段分割；Coronary Artery； Full Convolutional Neural Network； Two-Stage Segmentation
摘要: 计算机断层扫描血管造影(Computed tomography angiography, CTA)由于其成像具有高分辨率以及无创性而被用于冠状动脉疾病诊断和治疗中，精准的冠状动脉分割对冠状动脉病变的诊断和治疗具有重要的作用。本文提出了一种基于两阶段全卷积神经网络的冠状动脉分割方法，有效地利用粗分割指导切块分割并进一步提升分割准确率。实验表明，本文的方法相比于其他常规的分割方法有一定的性能提升。
Abstract: Computed tomography angiography (CTA) is used in the diagnosis and treatment of coronary artery disease due to its high resolution and non-invasive nature. Accurate coronary artery segmentation plays an important role in the diagnosis and treatment of coronary artery lesions. In this study, a two-stage fully convolutional neural network-based coronary artery segmentation model is proposed to effectively use coarse segmentation to guide fine segmentation, thereby improving accu-racy. Experiments show that the method in this paper has a large performance improvement compared to other single-stage segmentation methods.
文章引用：吴春彪. 基于两阶段全卷积神经网络的冠状动脉分割研究[J]. 计算机科学与应用, 2022, 12(4): 828-834. https://doi.org/10.12677/CSA.2022.124084

参考文献

[1] 国家心血管病中心. 中国心血管健康与疾病报告2020 [M]. 北京: 科学出版社, 2021.
[2] 刘昊, 王瑜, 王怡宁, 徐橙. 冠状动脉血管造影图像三维分割方法[J]. 中国医学物理学杂志, 2021, 38(7): 826-830.
[3] 黄山, 程晓光. 基于水平集方法的冠状动脉CT图像分割[J]. 北京生物医学工程, 2020, 39(6): 569-573+581.
[4] 姜伟, 吕晓琪, 任晓颖, 任国印. 结合区域生长与图割算法的冠状动脉CT血管造影图像三维分割[J]. 计算机应用, 2015, 35(5): 1462-1466.
[5] 黎丽华, 黄岳山, 杨荣骞, 吴效明. 基于双源CT图像的冠状动脉分割[J]. 中国组织工程研究, 2012, 16(39): 7298-7301.
[6] Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2017) ImageNet Classification with Deep Convolutional Neural Networks. Communications of the ACM, 60, 84-90. [Google Scholar] [CrossRef] 
[7] Long, J., Shelhamer, E. and Darrell, T. (2015) Fully Convolutional Net-works for Semantic Segmentation. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recogni-tion, Boston, 7-12 June 2015, 3431-3440. [Google Scholar] [CrossRef] 
[8] 康皓贝, 孙耀宗, 陈杰. 基于深度卷积网络的冠脉血管分割方法[J]. 电子技术与软件工程, 2020(6): 140-144.
[9] 冯雪聪, 陈波, 钱俊磊, 曾凯, 陈伟彬, 李晓琳, 潘红红. 基于深度学习的CTA影像冠状动脉分割[J]. 激光杂志, 2022, 43(2): 200-204. [Google Scholar] [CrossRef] 
[10] Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, 5-9 October 2015, 234-241. [Google Scholar] [CrossRef] 
[11] 沈烨, 方志军, 高永彬. 嵌入注意力机制的多模型融合冠脉CTA分割算法[J]. 计算机科学与探索, 2019, 14(9): 1602-1611.
[12] Schlemper, J., Oktay, O., Chen, L., Matthew, J., Knight, C., Kainz, B., et al. (2018) Attention-Gated Networks for Improving Ultrasound Scan Plane Detection. 2018 International Conference on Medical Image Computing and Computer-Assisted Intervention, Granada, 16-20 September 2018.
[13] Huang, W., Huang, L., Lin, Z., Huang, S., Chi, Y., Zhou, J., et al. (2018) Coronary Artery Segmentation by Deep Learning Neural Networks on Computed Tomographic Coronary Angiographic Images. 2018 40th Annual interna-tional conference of the IEEE Engineering in Medicine and Biology Society, Honolulu, 18-21 July 2018, 608-611. [Google Scholar] [CrossRef] 
[14] Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T. and Ronneberger, O. (2016) 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. International Conference on Medical Image Computing and Computer-Assisted Intervention, Athens, 17-21 October 2016, 424-432. [Google Scholar] [CrossRef] 
[15] Kong, B., Wang, X., Bai, J., Lu, Y., Gao, F., Cao, K., et al. (2020) Learning Tree-Structured Representation for 3D Coronary Artery Segmentation. Computerized Medical Imaging and Graphics, 80, Article ID: 101688. [Google Scholar] [CrossRef] [PubMed]