AngioNet: a convolutional neural network for vessel segmentation in X-ray angiography.

AngioNet: a convolutional neural network for vessel segmentation in X-ray angiography.
复制标题

DOI:
10.1038/s41598-021-97355-8
复制
发表时间:
2021-09-10
期刊:
影响因子:
4.6
通讯作者:
Figueroa CA
Figueroa CA
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Iyer K;Najarian CP;Fattah AA;Arthurs CJ;Soroushmehr SMR;Subban V;Sankardas MA;Nadakuditi RR;Nallamothu BK;Figueroa CA

文献摘要

参考文献

被引文献

相似文献

冠状动脉疾病 (CAD) 通常使用 X 射线血管造影进行诊断,在X射线血管造影中,当不透射线的染料冲过冠状血管时拍摄图像,以可视化血管变窄或狭窄的严重程度。心脏病专家通常使用视觉估计来估算狭窄直径减少的百分比,这可以指导支架置入等治疗。全自动的血管分段方法将消除潜在的主观性,并提供直径减小的定量和系统测量。在这里,我们设计了一个卷积神经网络 AngioNet,用于 X 射线血管造影图像中的血管分割。该网络的主要创新是引入了血管造影处理网络(APN),它显着提高了多个网络主干上的分割性能,其中使用 Deeplabv3+ 的性能最佳(Dice 得分 0.864,像素精度 0.983,灵敏度 0.918,特异性 0.987)。 APN 的目的是为图像预处理和分割创建端到端管道,学习最佳的预处理滤波器以改进分割。我们还展示了我们的网络在通过定量冠状动脉造影测量血管直径方面的可互换性。我们的结果表明,AngioNet 是自动血管造影血管分割的强大工具,可以促进临床工作流程中冠状动脉狭窄的系统解剖学评估。
Coronary Artery Disease (CAD) is commonly diagnosed using X-ray angiography, in which images are taken as radio-opaque dye is flushed through the coronary vessels to visualize the severity of vessel narrowing, or stenosis. Cardiologists typically use visual estimation to approximate the percent diameter reduction of the stenosis, and this directs therapies like stent placement. A fully automatic method to segment the vessels would eliminate potential subjectivity and provide a quantitative and systematic measurement of diameter reduction. Here, we have designed a convolutional neural network, AngioNet, for vessel segmentation in X-ray angiography images. The main innovation in this network is the introduction of an Angiographic Processing Network (APN) which significantly improves segmentation performance on multiple network backbones, with the best performance using Deeplabv3+ (Dice score 0.864, pixel accuracy 0.983, sensitivity 0.918, specificity 0.987). The purpose of the APN is to create an end-to-end pipeline for image pre-processing and segmentation, learning the best possible pre-processing filters to improve segmentation. We have also demonstrated the interchangeability of our network in measuring vessel diameter with Quantitative Coronary Angiography. Our results indicate that AngioNet is a powerful tool for automatic angiographic vessel segmentation that could facilitate systematic anatomical assessment of coronary stenosis in the clinical workflow.
DOI: 10.1016/j.patrec.2003.08.001
发表时间: 2003-12-01
影响因子: 5.1
作者:
Cañero, C;Radeva, P
通讯作者: Radeva, P
DOI: 10.1002/sim.3697
发表时间: 2009-11-10
影响因子: 2
作者:
Austin, Peter C.
通讯作者: Austin, Peter C.
DOI: 10.1109/42.848183
发表时间: 2000-04-01
影响因子: 10.6
作者:
Chen, SJ;Carroll, JD
通讯作者: Carroll, JD
DOI: 10.1109/titb.2012.2220781
发表时间: 2012-11-01
影响因子: --
作者:
Hernandez-Vela, Antonio;Gatta, Carlo;Radeva, Petia
通讯作者: Radeva, Petia
DOI: 10.3390/app9245507
发表时间: 2019-12-01
影响因子: 2.7
作者:
Cervantes-Sanchez, Fernando;Cruz-Aceves, Ivan;Eduardo Solorio-Meza, Sergio
通讯作者: Eduardo Solorio-Meza, Sergio