BIDMIR: BI-DIRECTIONAL MEDICAL IMAGE REGISTRATION WITH SYMMETRIC ATTENTION AND CYCLIC CONSISTENCY REGULARIZATION

被引:0
作者
Gao, Xiaoru [1 ]
Tao, Rong [1 ]
Zheng, Guoyan [1 ]
机构
[1] Shanghai Jiao Tong Univ, Sch Biomed Engn, Inst Med Robot, Shanghai, Peoples R China
来源
2022 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (IEEE ISBI 2022) | 2022年
关键词
Deep learning; Bi-directional medical image registration; Symmetric attention; Cyclic consistency; LEARNING FRAMEWORK;
D O I
10.1109/ISBI52829.2022.9761636
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
The past years witness the remarkable progress in developing deep learning-based image registration methods, which leverage convolutional neural networks (CNNs) for efficient and end-to-end regression of deformation fields from an image pair. Identified limitations of existing methods include (a) ignorance of intra- and inter-image long-range spatial relevance, leading to failure in finding semantically meaningful correspondences of anatomical structures; and (b) single direction of image registration with no enforcement of topology preservation, resulting in loss of structural information. To address these issues, we propose a novel bi-directional medical image registration method, referred as BIDMIR, integrating symmetric attention with cyclic consistency regularization. The proposed method consists of a learnable volumetric embedding module, a symmetric attention module for feature enhancement, and a bi-directional registration field inference module. The symmetric attention module explicitly models the intra- and inter-image long-range relevance in the embedding, facilitating bi-directional correspondence of semantically meaningful structures. Cyclic consistency regularization is additionally proposed to encourage topology preservation. Results demonstrate the efficacy of our approach.
引用
收藏
页数:5
相关论文
共 19 条
  • [1] Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain
    Avants, B. B.
    Epstein, C. L.
    Grossman, M.
    Gee, J. C.
    [J]. MEDICAL IMAGE ANALYSIS, 2008, 12 (01) : 26 - 41
  • [2] VoxelMorph: A Learning Framework for Deformable Medical Image Registration
    Balakrishnan, Guha
    Zhao, Amy
    Sabuncu, Mert R.
    Guttag, John
    Dalca, Adrian, V
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2019, 38 (08) : 1788 - 1800
  • [3] Deformable Image Registration Using a Cue-Aware Deep Regression Network
    Cao, Xiaohuan
    Yang, Jianhua
    Zhang, Jun
    Wang, Qian
    Yap, Pew-Thian
    Shen, Dinggang
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2018, 65 (09) : 1900 - 1911
  • [4] Chen JY, 2021, Arxiv, DOI arXiv:2104.06468
  • [5] Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces
    Dalca, Adrian V.
    Balakrishnan, Guha
    Guttag, John
    Sabuncu, Mert R.
    [J]. MEDICAL IMAGE ANALYSIS, 2019, 57 : 226 - 236
  • [6] A deep learning framework for unsupervised affine and deformable image registration
    de Vos, Bob D.
    Berendsen, Floris F.
    Viergever, Max A.
    Sokooti, Hessam
    Staring, Marius
    Isgum, Ivana
    [J]. MEDICAL IMAGE ANALYSIS, 2019, 52 : 128 - 143
  • [7] FreeSurfer
    Fischl, Bruce
    [J]. NEUROIMAGE, 2012, 62 (02) : 774 - 781
  • [8] CycleMorph: Cycle consistent unsupervised deformable image registration
    Kim, Boah
    Kim, Dong Hwan
    Park, Seong Ho
    Kim, Jieun
    Lee, June-Goo
    Ye, Jong Chul
    [J]. MEDICAL IMAGE ANALYSIS, 2021, 71
  • [9] Multiresolution elastic image registration
    Kostelec, PJ
    Weaver, JB
    Healy, DM
    [J]. MEDICAL PHYSICS, 1998, 25 (09) : 1593 - 1604
  • [10] Open access series of imaging studies (OASIS): Cross-sectional MRI data in young, middle aged, nondemented, and demented older adults
    Marcus, Daniel S.
    Wang, Tracy H.
    Parker, Jamie
    Csernansky, John G.
    Morris, John C.
    Buckner, Randy L.
    [J]. JOURNAL OF COGNITIVE NEUROSCIENCE, 2007, 19 (09) : 1498 - 1507