《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (5): 1596-1605.DOI: 10.11772/j.issn.1001-9081.2022040536

• 多媒体计算与计算机仿真 • 上一篇    

基于Transformer的结构强化IVOCT导丝伪影去除方法

郭劲文1, 马兴华1, 骆功宁1, 王玮1, 曹阳2, 王宽全1()   

  1. 1.哈尔滨工业大学 计算学部,哈尔滨 150001
    2.哈尔滨医科大学附属第一医院,哈尔滨 150001
  • 收稿日期:2022-04-21 修回日期:2022-07-05 接受日期:2022-07-08 发布日期:2022-08-05 出版日期:2023-05-10
  • 通讯作者: 王宽全
  • 作者简介:郭劲文(1997—),男,宁夏银川人,硕士研究生,主要研究方向:医学图像处理、计算机视觉
    马兴华(1998—),男,黑龙江哈尔滨人,硕士研究生,主要研究方向:计算机视觉、医学图像分析
    骆功宁(1989—),男,山东烟台人,副教授,博士,主要研究方向:计算心脏学、医学图像分析
    王玮(1989—),女,四川达州人,助理教授,博士,主要研究方向:虚拟心脏、医学图像处理
    曹阳(1984—),男,黑龙江人,教授,博士,主要研究方向:冠心病诊疗、冠脉介入治疗
    王宽全(1964—),男,四川达州人,教授,博士,CCF会员,主要研究方向:虚拟现实与仿真、计算心脏学、人工智能与智慧医疗。wangkq@hit.edu.cn
  • 基金资助:
    国家自然科学基金资助项目(62001141);哈尔滨工业大学第七批教学发展基金资助项目(XYSZ2021048)

Guidewire artifact removal method of structure-enhanced IVOCT based on Transformer

Jinwen GUO1, Xinghua MA1, Gongning LUO1, Wei WANG1, Yang CAO2, Kuanquan WANG1()   

  1. 1.Faculty of Computing,Harbin Institute of Technology,Harbin Heilongjiang 150001,China
    2.The First Affiliated Hospital of Harbin Medical University,Harbin Heilongjiang 150001,China
  • Received:2022-04-21 Revised:2022-07-05 Accepted:2022-07-08 Online:2022-08-05 Published:2023-05-10
  • Contact: Kuanquan WANG
  • About author:GUO Jinwen, born in 1997, M. S. candidate. His research interests include medical image processing, computer vision.
    MA Xinghua, born in 1998, M. S. candidate. His research interests include computer vision, medical image analysis.
    LUO Gongning, born in 1989, Ph. D., associate professor. His research interests include computational cardiology, medical image analysis.
    WANG Wei, born in 1989, Ph. D., assistant professor. Her research interests include virtual heart, medical image processing.
    CAO Yang, born in 1984, Ph. D., professor. His research interests include coronary artery disease diagnosis/treatment, coronary interventional therapy.
    WANG Kuanquan, born in 1964, Ph. D., professor. His research interests include virtual reality and simulation, computational cardiology, artificial intelligence and smart healthcare.
  • Supported by:
    National Natural Science Foundation of China(62001141);the Seventh Batch of Teaching Development Fund Projects in Harbin Institute of Technology(XYSZ2021048)

摘要:

为去除导丝伪影以提高血管内光学相干断层扫描(IVOCT)的图像质量,辅助医师更加准确地诊断心血管疾病,降低误诊及漏诊的概率,针对IVOCT图像结构信息复杂且伪影区域占比大的难点,提出一种采用生成对抗网络(GAN)架构的基于Transformer的结构强化网络(SETN)。首先,GAN的生成器在提取纹理特征的原始图像(ORI)主干生成网络的基础上,并联了RTV(Relative Total Variation)图像强化生成网络用于获取图像的结构信息;其次,在ORI/RTV图像的伪影区域重建过程中,引入了分别关注时/空间域信息的Transformer编码器,用于捕获IVOCT图像序列的上下文信息以及纹理/结构特征之间的关联性;最后,利用结构特征融合模块将不同层次的结构特征融入ORI主干生成网络的解码阶段,配合判别器完成导丝伪影区域的图像重建。实验结果表明,SETN的导丝伪影去除结果在纹理和结构的重建上均十分优秀。此外,导丝伪影去除后IVOCT图像质量的提高,对于IVOCT图像的易损斑块分割及管腔轮廓线提取任务均具有积极意义。

关键词: 生成对抗网络, Transformer, 结构强化, 血管内光学相干断层扫描, 伪影去除

Abstract:

Improving the image quality of IntraVascular Optical Coherence Tomography (IVOCT) through guidewire artifact removal can assist physicians in diagnosing cardiovascular diseases more accurately, which reduces the probabilities of misdiagnosis and missed diagnosis. Aiming at the difficulties of complex structure information and a large proportion of artifact areas in IVOCT images, a Structure-Enhanced Transformer Network (SETN) using Generative Adversarial Network (GAN) architecture was proposed for guidewire artifact removal of IVOCT images. Firstly, based on the ORiginal Image (ORI) backbone generation network for extracting texture features, the generator of GAN was combined with RTV (Relative Total Variation) image enhanced generation network in parallel to obtain image structure information. Next, during the artifact area reconstruction of ORI/RTV image, Transformer encoders focusing on the temporal/spatial domain information respectively were introduced to capture the contextual information and the correlation between texture/structure features of IVOCT image sequence. Finally, the structural feature fusion module was used to integrate the structural features of different levels into the decoding stage of the ORI backbone generation network, so that the generator was cooperated with the discriminator for completing the image reconstruction of the guidewire artifact area. Experimental results show that the guidewire artifact removal results of SETN are excellent in both texture and structure reconstruction. Besides, the improvement of IVOCT image quality after guidewire artifact removal is positive for both vulnerable plaque segmentation and lumen contour extraction tasks of IVOCT image.

Key words: Generative Adversarial Network (GAN), Transformer, structure enhancement, IntraVascular Optical Coherence Tomography (IVOCT), artifact removal

中图分类号: