Recursive Centerline- and Direction-Aware Joint Learning Network with Ensemble Strategy for Vessel Segmentation in X-ray Angiography Images
Recursive Centerline- and Direction-Aware Joint Learning Network with Ensemble Strategy for Vessel Segmentation in X-ray Angiography Images
复制标题
具有集成策略的递归中心线和方向感知联合学习网络用于 X 射线血管造影图像中的血管分割
DOI：
10.1016/j.cmpb.2022.106787
复制
发表时间：
2022-04
影响因子：
6.1
通讯作者：
Jian Yang
中科院分区：
文献类型：
--
作者：
Tao Han;Danni Ai;Yining Wang;Yonglin Bian;Ruirui An;Jingfan Fan;Hong Song;Hongzhi Xie;Jian Yang
背景与目的血管自动分割是心血管疾病诊断和治疗的重要研究课题。主要的挑战是如何从低质量和高复杂度的XRA图像中提取连续和完整的血管结构。现有的分割方法主要集中在像素级的分割上，忽略了图像的几何特征，导致分割结果的不完整和缺失。为了提高血管分割的完整性和准确性，我们提出了一个递归的联合学习网络嵌入几何features.MethodsThe网络加入的中心线和方向意识的辅助任务与分割的主要任务，引导网络探索血管连通性的几何特征。此外，递归学习策略的设计，通过传递到同一个网络迭代以前的分割结果，以提高分割。为了进一步提高连通性，我们提出了一个互补的任务集成策略，通过融合的三个任务的最终分割结果与majority voting.ResultsTo验证我们的方法的有效性，我们进行定性和定量的XRA图像的冠状动脉和主动脉，包括主动脉弓，胸主动脉，腹主动脉。我们的方法实现的F1分数为85.61±3.48%的冠状动脉，89.02±2.89%的主动脉弓，88.22±3.33%的胸主动脉，83.12± 4.61%.ConclusionsCompared相比，六个国家的最先进的方法，我们的方法显示了最完整和准确的血管分割结果。
Background and objectiveAutomatic vessel segmentation from X-ray angiography images is an important research topic for the diagnosis and treatment of cardiovascular disease. The main challenge is how to extract continuous and completed vessel structures from XRA images with poor quality and high complexity. Most existing methods predominantly focus on pixel-wise segmentation and overlook the geometric features, resulting in breaking and absence in segmentation results. To improve the completeness and accuracy of vessel segmentation, we propose a recursive joint learning network embedded with geometric features.MethodsThe network joins the centerline- and direction-aware auxiliary tasks with the primary task of segmentation, which guides the network to explore the geometric features of vessel connectivity. Moreover, the recursive learning strategy is designed by passing the previous segmentation result into the same network iteratively to improve segmentation. To further enhance connectivity, we present a complementary-task ensemble strategy by fusing the outputs of the three tasks for the final segmentation result with majority voting.ResultsTo validate the effectiveness of our method, we conduct qualitative and quantitative experiments on the XRA images of the coronary artery and aorta including aortic arch, thoracic aorta, and abdominal aorta. Our method achieves F1scores of 85.61±3.48% for the coronary artery, 89.02±2.89% for the aortic arch, 88.22±3.33% for the thoracic aorta, and 83.12±4.61% for the abdominal aorta.ConclusionsCompared with six state-of-the-art methods, our method shows the most complete and accurate vessel segmentation results.
登录
查看更多内容
DOI：
10.1109/tcsvt.2019.2892986
发表时间：
2020-02
影响因子：
8.4
作者：
Huihui Fang;Danni Ai;Weijian Cong;Siyuan Yang;Jianjun Zhu;Yong Huang;Hong Song;Yongtian Wang;Jian Yang
通讯作者：
Huihui Fang;Danni Ai;Weijian Cong;Siyuan Yang;Jianjun Zhu;Yong Huang;Hong Song;Yongtian Wang;Jian Yang
DOI：
10.1609/aaai.v34i07.6946
发表时间：
2019-12
期刊：
ArXiv
影响因子：
--
作者：
Yuan Xue;Hui Tang;Zhi Qiao;G. Gong;Yong Yin;Zhen Qian;Chao Huang;Wei Fan;Xiaolei Huang
通讯作者：
Yuan Xue;Hui Tang;Zhi Qiao;G. Gong;Yong Yin;Zhen Qian;Chao Huang;Wei Fan;Xiaolei Huang
DOI：
10.1145/3458380.3458383
发表时间：
2021-02
期刊：
Proceedings of the 2021 5th International Conference on Digital Signal Processing
影响因子：
--
作者：
Tao Han;Yonglin Bian;Ruirui An;Yechen Han;Danni Ai;Jian Yang
通讯作者：
Tao Han;Yonglin Bian;Ruirui An;Yechen Han;Danni Ai;Jian Yang
影响因子：
3.2
作者：
Fazlali, Hamid R.;Karimi, Nader;Najarian, Kayvan
通讯作者：
Najarian, Kayvan
DOI：
10.1109/tpami.2018.2858826
发表时间：
2020-02-01
影响因子：
23.6
作者：
Lin, Tsung-Yi;Goyal, Priya;Dollar, Piotr
通讯作者：
Dollar, Piotr