[논문]CycleMorph: Cycle consistent unsupervised deformable image registration

Kim, Boah; Kim, Dong Hwan; Park, Seong Ho; Kim, Jieun; Lee, June-Goo; Ye, Jong Chul

doi:10.1016/j.media.2021.102036

[해외논문] CycleMorph: Cycle consistent unsupervised deformable image registration 원문보기

Medical image analysis, v.71, 2021년, pp.102036 -

Kim, Boah (Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology (KAIST)) , Kim, Dong Hwan (Department of Radiology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea) , Park, Seong Ho (Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center) , Kim, Jieun (Smart Car R&D Division, AI-Bigdata R&D Center, Korea Automotive Technology Institute (KATECH)) , Lee, June-Goo (Department of Convergence Medicine, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine) , Ye, Jong Chul (Corresponding author.)

Abstract ▼ AI-Helper

Abstract Image registration is a fundamental task in medical image analysis. Recently, many deep learning based image registration methods have been extensively investigated due to their comparable performance with the state-of-the-art classical approaches despite the ultra-fast computational time. However, the existing deep learning methods still have limitations in the preservation of original topology during the deformation with registration vector fields. To address this issues, here we present a cycle-consistent deformable image registration, dubbed CycleMorph. The cycle consistency enhances image registration performance by providing an implicit regularization to preserve topology during the deformation. The proposed method is so flexible that it can be applied for both 2D and 3D registration problems for various applications, and can be easily extended to multi-scale implementation to deal with the memory issues in large volume registration. Experimental results on various datasets from medical and non-medical applications demonstrate that the proposed method provides effective and accurate registration on diverse image pairs within a few seconds. Qualitative and quantitative evaluations on deformation fields also verify the effectiveness of the cycle consistency of the proposed method. Highlights Cycle consistency provides an implicit regularization of the deformation. Imposing the cycle consistency on images improves topological preservation. The proposed method is flexible for 2D and 3D image registration problems. Multi-scale implementation deals with the memory issues in large volume registration. Graphical abstract [DISPLAY OMISSION]

Keyword

참고문헌 (36)

Neuroimage Ashburner 38 1 95 2007 10.1016/j.neuroimage.2007.07.007 A fast diffeomorphic image registration algorithm

상세보기
Med. Image Anal. Avants 12 1 26 2008 10.1016/j.media.2007.06.004 Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain

상세보기
Neuroimage Avants 54 3 2033 2011 10.1016/j.neuroimage.2010.09.025 A reproducible evaluation of ants similarity metric performance in brain image registration

상세보기
Balakrishnan 9252 2018 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition An unsupervised learning model for deformable medical image registration
IEEE Trans. Med. Imaging Balakrishnan 38 8 1788 2019 10.1109/TMI.2019.2897538 Voxelmorph: a learning framework for deformable medical image registration

상세보기
Int. J. Comput. Vis. Beg 61 2 139 2005 10.1023/B:VISI.0000043755.93987.aa Computing large deformation metric mappings via geodesic flows of diffeomorphisms

상세보기
arXiv preprint arXiv:1804.10735 Cao 2018 Deep learning based inter-modality image registration supervised by intra-modality similarity
Cao 300 2017 International Conference on Medical Image Computing and Computer-Assisted Intervention Deformable image registration based on similarity-steered cnn regression
IEEE Trans. Med. Imaging Cao 24 9 1216 2005 10.1109/TMI.2005.853923 Large deformation diffeomorphic metric mapping of vector fields

상세보기
Neuroimage Ceritoglu 47 2 618 2009 10.1016/j.neuroimage.2009.04.057 Multi-contrast large deformation diffeomorphic metric mapping for diffusion tensor imaging

상세보기
IEEE Trans. Med. Imaging Christensen 20 7 568 2001 10.1109/42.932742 Consistent image registration

상세보기
Dalca 729 2018 International Conference on Medical Image Computing and Computer-Assisted Intervention Unsupervised learning for fast probabilistic diffeomorphic registration
Fan 739 2018 International Conference on Medical Image Computing and Computer-Assisted Intervention Adversarial similarity network for evaluating image alignment in deep learning based registration
Neuroimage Fischl 62 2 774 2012 10.1016/j.neuroimage.2012.01.021 Freesurfer

상세보기
Goodfellow 2672 2014 Advances in neural information processing systems Generative adversarial nets
Jaderberg 2017 2015 Advances in neural information processing systems Spatial transformer networks
Kim 166 2019 International Conference on Medical Image Computing and Computer-Assisted Intervention Unsupervised deformable image registration using cycle-consistent cnn
Abdom. Imaging Kim 36 3 300 2011 10.1007/s00261-011-9683-3 Assessment of the treatment response of hcc

상세보기
IEEE Trans. Med. Imaging Klein 29 1 196 2009 10.1109/TMI.2009.2035616 Elastix: a toolbox for intensity-based medical image registration

상세보기
arXiv preprint arXiv:1804.07172 Krebs 2018 Learning structured deformations using diffeomorphic registration
Alzheimer’s & Dementia: The Journal of the Alzheimer’s Association LaMontagne 14 7 P1097 2018 Oasis-3: longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and alzheimers disease

상세보기
Cognition and emotion Langner 24 8 1377 2010 10.1080/02699930903485076 Presentation and validation of the radboud faces database

상세보기
Physics in Medicine & Biology Lei 2020 4D-ct deformable image registration using multiscale unsupervised deep learning
Leow 493 2005 Biennial International Conference on Information Processing in Medical Imaging Inverse consistent mapping in 3d deformable image registration: its construction and statistical properties
Mahapatra 1449 2018 Biomedical Imaging (ISBI 2018), 2018 IEEE 15th International Symposium on Deformable medical image registration using generative adversarial networks
Onofrey 13 2013 International MICCAI Workshop on Medical Computer Vision Semi-supervised learning of nonrigid deformations for image registration
Rohé 266 2017 International Conference on Medical Image Computing and Computer-Assisted Intervention Svf-net: Learning deformable image registration using shape matching
Ronneberger 234 2015 International Conference on Medical image computing and computer-assisted intervention U-net: Convolutional networks for biomedical image segmentation
Sokooti 232 2017 International Conference on Medical Image Computing and Computer-Assisted Intervention Nonrigid image registration using multi-scale 3d convolutional neural networks
Neuroimage Vercauteren 45 1 S61 2009 10.1016/j.neuroimage.2008.10.040 Diffeomorphic demons: efficient non-parametric image registration

상세보기
Med Image Anal de Vos 52 128 2019 10.1016/j.media.2018.11.010 A deep learning framework for unsupervised affine and deformable image registration

상세보기
Neuroimage Yang 158 378 2017 10.1016/j.neuroimage.2017.07.008 Quicksilver: fast predictive image registration-a deep learning approach

상세보기
arXiv preprint arXiv:1809.03443 Zhang 2018 Inverse-consistent deep networks for unsupervised deformable image registration
Image Vis. Comput. Zhang 26 2 201 2008 10.1016/j.imavis.2007.04.003 Rapid surface registration of 3d volumes using a neural network approach

상세보기
Zhang 559 2017 International conference on information processing in medical imaging Frequency diffeomorphisms for efficient image registration
Zhu 2223 2017 Proceedings of the IEEE international conference on computer vision Unpaired image-to-image translation using cycle-consistent adversarial networks

LOADING...

활용도 분석정보

상세보기

다운로드

내보내기

활용도 Top5 논문

해당 논문의 주제분야에서 활용도가 높은 상위 5개 콘텐츠를 보여줍니다.
더보기 버튼을 클릭하시면 더 많은 관련자료를 살펴볼 수 있습니다.

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증