The extraction of contrast-filled vessels from X-ray coronary angiography(XCA) image sequence has important clinical significance for intuitively diagnosis and therapy. In this study, XCA image sequence O is regarded as a three-dimensional tensor input, vessel layer H is a sparse tensor, and background layer B is a low-rank tensor. Using tensor nuclear norm(TNN) minimization, a novel method for vessel layer extraction based on tensor robust principal component analysis(TRPCA) is proposed. Furthermore, considering the irregular movement of vessels and the dynamic interference of surrounding irrelevant tissues, the total variation(TV) regularized spatial-temporal constraint is introduced to separate the dynamic background E. Subsequently, for the vessel images with uneven contrast distribution, a two-stage region growth(TSRG) method is utilized for vessel enhancement and segmentation. A global threshold segmentation is used as the pre-processing to obtain the main branch, and the Radon-Like features(RLF) filter is used to enhance and connect broken minor segments, the final vessel mask is constructed by combining the two intermediate results. We evaluated the visibility of TV-TRPCA algorithm for foreground extraction and the accuracy of TSRG algorithm for vessel segmentation on real clinical XCA image sequences and third-party database. Both qualitative and quantitative results verify the superiority of the proposed methods over the existing state-of-the-art approaches.
翻译:从X射线冠心血管动脉学(XCA)图像中提取装有对比的容器,对于直觉诊断和治疗具有重要的临床意义。在本研究中,XCA图像序列O被视为三维感光输入,容器层H是一个稀疏的强度,背景层B是一个低的强度。利用高温核规范(TNN)最小化,提出了一种根据强强力主要成分分析(TRPCA)提取船只层的新颖方法。此外,考虑到船只的不规则移动和周围无关组织动态干扰,引入了完全变异(TV)常规空间时空限制来分离动态背景E。随后,对于对比分布不均匀的船舶图像,采用了两阶段区域增长法(TSRG)用于船只的增强和分解。使用全球临界分解作为预处理以获得主分支,而拟议的拉东类似特性用于加强和连接小块断裂的小型部分,最后的容器面罩是结合两种中间结果。我们评估了目前SVTRPCA-CA级定序和TV-CA-CA-R-S-S-S-R-R-R-CAR-R-R-R-C-R-R-R-R-R-R-R-R-C-R-C-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-R-