[1]WANG Ru,SUN Zheng,YAO Yue.Unsupervised deep learning method for suppressing motion artifacts in cardiac vascular image sequences[J].CAAI Transactions on Intelligent Systems,2025,20(4):984-998.[doi:10.11992/tis.202408014]
Copy

Unsupervised deep learning method for suppressing motion artifacts in cardiac vascular image sequences

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 20 Number of periods: 2025 4 Page number: 984-998 Column: 学术论文—机器学习 Public date: 2025-08-05
Title:
Unsupervised deep learning method for suppressing motion artifacts in cardiac vascular image sequences
Author(s):
WANG Ru1;  SUN Zheng1; 2;  YAO Yue1
1. Department of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, China;
2. Hebei Key Laboratory of Power Internet of Things Technology, North China Electric Power University, Baoding 071003, China
Keywords:
cardiac vascular imaging; intracoronary imaging; image sequences; motion artifact; motion compensation; neural network; unsupervised learning; elastic registration
CLC:
TP391.41; R445
DOI:
10.11992/tis.202408014
Abstract:
Intravascular ultrasound (IVUS) and optical coherence tomography (OCT) are important tools for diagnosing coronary atherosclerotic lesions. However, cardiac motion and pulsatile blood flow can cause motion artifacts that affect image quality. To address this issue, an unsupervised deep learning method for suppressing motion artifacts in IVUS/OCT image sequences is proposed in this paper. A deep neural network consisting of feature extraction, upsampling, motion estimation, and motion correction modules is designed, and it can map continuous pullback image sequences to artifact-free image sequences. The network is trained in an unsupervised manner using clinical IVUS/OCT images. Experimental results demonstrate that this method remarkably improves the smoothness of the vessel wall boundaries in the longitudinal view, with substantial improvements in standard deviation and interframe dissimilarity metrics. Compared with other methods, the proposed approach reduces average interframe dissimilarity and standard deviation by approximately 23% and 24%, respectively. This method effectively solves the image quality degradation caused by motion artifacts in IVUS/OCT image sequences and optimizes the visual quality of the images.
References:
[1] SUWANNASOM P, CHICHAREON P, ROONGSANGMANOON W, et al. Impact of the adjunctive use criteria for intravascular ultrasound-guided percutaneous coronary intervention and clinical outcomes[J]. Scientific reports, 2023, 13(1): 711-711.
[2] MOHAN N C, JOHNSON T W. Intracoronary optical coherence tomography—an introduction[J]. Catheterization and cardiovascular interventions, 100(S1): S57-S65.
[3] LENG J, ZHANG J, LI C, et al. Multi-spectral intravascular photoacoustic/ultrasound/optical coherence tomography tri-modality system with a fully-integrated 0.9-mm full field-of-view catheter for plaque vulnerability imaging[J]. Biomedical optics express, 2021, 12(4): 1934-1946.
[4] KERMANI A, AYATOLLAHI A, TAKI A. Novel coronary tortuosity extraction using intravascular ultrasound sequence alone[C]//IEEE 2017 24th National and 2nd International Iranian Conference on Biomedical Engineering. Tehran: IEEE, 2017: 47-50.
[5] NIKOPOULOS S, PAPAFAKLIS MI, TSOMPOU P, et al. Virtual hemodynamic assessment of coronary lesions: the advent of functional angiography and coronary imaging[J]. Journal of clinical medicine, 2024, 13(8): 2243.
[6] TIAN Jinwei, PENG Xiang, ZHANG Yanwen, et al. In vivo detection of cholesterol crystals in atherosclerotic plaque with optical coherence tomography[C]//Cholesterol Crystals in Atherosclerosis and Other Related Diseases, Contemporary Cardiology. New York: Springer, 2023: 75-87.
[7] KYRIAKIDIS S, RIGAS G, KIGKA V, et al. An all-in-one tool for 2D atherosclerotic disease assessment and 3D coronary artery reconstruction[J]. Journal of cardiovascular development and disease, 2023, 10(3): 130.
[8] GAUR P, GRIECO A, FAINMAN Y. Multirate spectral domain optical coherence tomography[J]. IEEE photonics journal, 2023, 15(5): 1-10.
[9] JENSEN L O, THAYSSEN P. Accuracy of electrocardiographic-gated versus nongated volumetric intravascular ultrasound measurements of coronary arterial narrowing[J]. The American journal of cardiology, 2007, 99(2): 279-283.
[10] CECCHETTI L, WANG T, HOOGENDOORN A, et al. In-vitro and in-vivo imaging of coronary artery stents with Heartbeat OCT[J]. International journal of cardiovascular imaging, 2020, 36: 1021-1029.
[11] XIA Jun, CHEN Wanyi, MASLOV K, et al. Retrospective respiration-gated whole-body photoacoustic computed tomography of mice[J]. Journal of biomedical optics, 2014, 19(1): 016003.
[12] 孙正. 抑制冠状动脉内超声图像序列运动伪影的离线门控方法[J]. 光电子. 激光, 2010, 21(4): 632-638.
SUN Zheng. An off-line gating method for suppressing motion artifacts in intracoronary ultrasound image sequence[J]. Journal of optoelectronics·laser, 2010, 21(4): 632-638.
[13] SUN Zheng, DU Jiejie. Suppression of motion artifacts in intravascular photoacoustic image sequences[J]. Biomedical optics express, 2021, 12(11): 6909-6927.
[14] BAJAJ R, HUANG Xingru, KILIC Y, et al. A deep learning methodology for the automated detection of end-diastolic frames in intravascular ultrasound images[J]. International journal of cardiovascular imaging, 2021, 37(6): 1825-1837.
[15] SUN Zheng, YAO Yue, WANG Ru. An unsupervised deep learning framework for retrospective gating of catheter-based cardiac imaging[J]. IET signal processing, 2024: 5664618.
[16] DANILOUCHKINE M G, MASTIK F, VAN DER STEEN A F. A study of coronary artery rotational motion with dense scale-space optical flow in intravascular ultrasound[J]. Physics in medicine and biology, 2009, 54(6): 1397-1418.
[17] DANILOUCHKINE M G, MASTIK F, VAN DER STEEN A F. Improving IVUS palpography by incorporation of motion compensation based on block matching and optical flow[J]. IEEE transactions on ultrasonics ferroelectrics and frequency control, 2008, 55(11): 2392-2404.
[18] SUN Deqing, YANG Xiaodong, LIU Mingyu, et al. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 8934-8943.
[19] LUO Kunming, WANG Chuan, LIU Shuaicheng, et al. UPFlow: upsampling pyramid for unsupervised optical flow learning[C]//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 1045-1054.
[20] 张聪炫, 史世栋, 葛利跃, 等. 基于遮挡优化的金字塔块匹配光流估计方法[J]. 电子学报, 2023, 51(9): 2539-2548.
ZHANG Congxuan, SHI Shidong, GE Liyue, et al. Pyramid patch-matching optical flow estimation method based on occlusion optimization[J]. Acta electronica sinica, 2023, 51(9): 2539-2548.
[21] TALOU G D M, BLANCO P J, LARRABIDE I, et al. Registration methods for IVUS: transversal and longitudinal transducer motion compensation[J]. IEEE transactions on biomedical engineering, 2017, 64(4): 890-903.
[22] SUN Zheng, WANG Jianjian. Compensation of in-plane rigid motion for in vivo intracoronary ultrasound image sequence[J]. Computers in biology and medicine, 2013, 43(9): 1077-1085.
[23] 余升林, 吴彤, 葛明锋, 等. 循环一致性的无监督可变形图像配准方法[J]. 计算机辅助设计与图形学学报, 2023, 35(4): 516-524.
YU Shenglin, WU Tong, GE Mingfeng, et al. Unsupervised deformable image registration method with cyclic consistency[J]. Journal of computer-aided design & computer graphics, 2023, 35(4): 516-524.
[24] FU Yunguan, BROWN N M, SAEED S U, et al. DeepReg: a deep learning toolkit for medical image registration[J]. Journal of open source software, 2020, 5(55): 2705.
[25] JADERBERG M, SIMONYAN K, ZISSERMAN A, et al. Spatial Transformer networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. Montreal: MIT Press, 2015: 2017-2025.
[26] GüLER A R, TRIGEORGIS G, ANTONAKOS E, et al. DenseReg: fully convolutional dense shape regression in-the-wild[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 6799-6808.
[27] 赵华秋, 谢勤岚. 一种用于心脏运动估计的快速图像配准方法[J]. 中南民族大学学报 (自然科学版), 2023, 42(1): 120-127.
ZHAO Huaqiu, XIE Qinlan. A fast image registration method for cardiac motion estimation[J]. Journal of South-central Minzu University(Natural Science Edition), 2023, 42(1): 120-127.
[28] 黄鹏, 郭春生, 陈华华, 等. 基于深度学习的图像配准方法综述[J]. 杭州电子科技大学学报(自然科学版), 2020, 40(6): 37-44.
HUANG Peng, GUO Chunsheng, CHEN Huahua, et al. An overview of image registration methods based on depth learning[J]. Journal of Hangzhou Dianzi University( Natural Sciences), 2020, 40(6): 37-44.
[29] 陈建明, 曾祥津, 钟丽云, 等. 基于深度学习的图像配准方法研究进展[J]. 量子电子学报, 2022, 39(6): 899-926.
CHEN Jianming, ZENG Xiangjin, ZHONG Liyun, et al. Research progress of image registration methods based on deep learning[J]. Chinese journal of quantum electronics, 2022, 39(6): 899-926.
[30] 应时辉, 杨菀, 杜少毅, 等. 基于深度学习的医学影像配准综述[J]. 模式识别与人工智能, 2021, 34(4): 287-299.
YING Shihui, YANG Wan, DU Shaoyi, et al. Deep learning based medical image registration: a review[J]. Pattern recognition and artificial intelligence, 2021, 34(4): 287-299.
[31] 周勤, 王远军. 基于深度学习的医学图像配准研究进展[J]. 上海理工大学学报, 2021, 43(5): 421-428.
ZHOU Qin, WANG Yuanjun. Advances in medical image registration based on deep learning[J]. Journal of University of Shanghai for Science and Technology, 2021, 43(5): 421-428.
[32] SUN Zheng, DU Jiejie, YAO Yue, et al. A deep learning method for motion artifact correction in intravascular photoacoustic image sequence[J]. IEEE transactions on medical imaging, 2023, 42(1): 68-78.
[33] HUR J, ROTH S. Iterative residual refinement for joint optical flow and occlusion estimation[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 5747-5756.
[34] DE WINTER S A, HAMERS R, DEGERTEKIN M, et al. Retrospective image-based gating of intracoronary ultrasound images for improved quantitative analysis: the intelligate method[J]. Catheterization and cardiovascular interventions, 2004, 61(1): 84-94.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems