LABEL-DRIVEN WEAKLY-SUPERVISED LEARNING FOR MULTIMODAL DEFORMABLE IMAGE REGISTRATION

被引:0
作者
Hu, Yipeng [1 ,2 ]
Modat, Marc [1 ]
Gibson, Eli [1 ]
Ghavami, Nooshin [1 ]
Bonmati, Ester [1 ]
Moore, Caroline M. [3 ]
Emberton, Mark [3 ]
Noble, J. Alison [2 ]
Barratt, Dean C. [1 ,4 ]
Vercauteren, Tom [1 ,4 ]
机构
[1] UCL, Ctr Med Image Comp, London, England
[2] Univ Oxford, Inst Biomed Engn, Oxford, England
[3] UCL, Div Surg & Intervent Sci, London, England
[4] UCL, Wellcome EPSRC Ctr Intervent & Surg Sci, London, England
来源
2018 IEEE 15TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2018) | 2018年
关键词
multimodal medical image registration; convolutional neural network; weakly-supervised learning; image-guided intervention; prostate cancer; PROSTATE-CANCER; BIOPSY; MR;
D O I
暂无
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Spatially aligning medical images from different modalities remains a challenging task, especially for intraoperative applications that require fast and robust algorithms. We propose a weakly-supervised, label-driven formulation for learning 3D voxel correspondence from higher-level label correspondence, thereby bypassing classical intensity-based image similarity measures. During training, a convolutional neural network is optimised by outputting a dense displacement field (DDF) that warps a set of available anatomical labels from the moving image to match their corresponding counterparts in the fixed image. These label pairs, including solid organs, ducts, vessels, point landmarks and other ad hoc structures, are only required at training time and can be spatially aligned by minimising a cross-entropy function of the warped moving label and the fixed label. During inference, the trained network takes a new image pair to predict an optimal DDF, resulting in a fully-automatic, label-free, real-time and deformable registration. For interventional applications where large global transformation prevails, we also propose a neural network architecture to jointly optimise the global-and local displacements. Experiment results are presented based on cross-validating registrations of 111 pairs of T2-weighted magnetic resonance images and 3D transrectal ultrasound images from prostate cancer patients with a total of over 4000 anatomical labels, yielding a median target registration error of 4.2 mm on landmark centroids and a median Dice of 0.88 on prostate glands.
引用
收藏
页码:1070 / 1074
页数:5
相关论文
共 23 条
[11]  
Krebs Julian, 2017, Medical Image Computing and Computer Assisted Intervention MICCAI 2017. 20th International Conference. Proceedings: LNCS 10433, P344, DOI 10.1007/978-3-319-66182-7_40
[12]  
Liao R, 2017, AAAI CONF ARTIF INTE, P4168
[13]   REAL-TIME 2D/3D REGISTRATION VIA CNN REGRESSION [J].
Miao, Shun ;
Wang, Z. Jane ;
Zheng, Yefeng ;
Liao, Rui .
2016 IEEE 13TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI), 2016, :1430-1434
[14]   Magnetic Resonance Imaging/Ultrasound Fusion Guided Prostate Biopsy Improves Cancer Detection Following Transrectal Ultrasound Biopsy and Correlates With Multiparametric Magnetic Resonance Imaging [J].
Pinto, Peter A. ;
Chung, Paul H. ;
Rastinehad, Ardeshir R. ;
Baccala, Angelo A., Jr. ;
Kruecker, Jochen ;
Benjamin, Compton J. ;
Xu, Sheng ;
Yan, Pingkun ;
Kadoury, Samuel ;
Chua, Celene ;
Locklin, Julia K. ;
Turkbey, Baris ;
Shih, Joanna H. ;
Gates, Stacey P. ;
Buckner, Carey ;
Bratslavsky, Gennady ;
Linehan, W. Marston ;
Glossop, Neil D. ;
Choyke, Peter L. ;
Wood, Bradford J. .
JOURNAL OF UROLOGY, 2011, 186 (04) :1281-1285
[15]  
Rohe Marc-Michel, 2017, Medical Image Computing and Computer Assisted Intervention MICCAI 2017. 20th International Conference. Proceedings: LNCS 10433, P266, DOI 10.1007/978-3-319-66182-7_31
[16]   Nonrigid registration using free-form deformations: Application to breast MR images [J].
Rueckert, D ;
Sonoda, LI ;
Hayes, C ;
Hill, DLG ;
Leach, MO ;
Hawkes, DJ .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 1999, 18 (08) :712-721
[17]   Magnetic Resonance Imaging/Ultrasound-Fusion Biopsy Significantly Upgrades Prostate Cancer Versus Systematic 12-core Transrectal Ultrasound Biopsy [J].
Siddiqui, M. Minhaj ;
Rais-Bahrami, Soroush ;
Hong Truong ;
Stamatakis, Lambros ;
Vourganti, Srinivas ;
Nix, Jeffrey ;
Hoang, Anthony N. ;
Walton-Diaz, Annerleim ;
Shuch, Brian ;
Weintraub, Michael ;
Kruecker, Jochen ;
Amalou, Hayet ;
Turkbey, Baris ;
Merino, Maria J. ;
Choyke, Peter L. ;
Wood, Bradford J. ;
Pinto, Peter A. .
EUROPEAN UROLOGY, 2013, 64 (05) :713-719
[18]   Rethinking the Inception Architecture for Computer Vision [J].
Szegedy, Christian ;
Vanhoucke, Vincent ;
Ioffe, Sergey ;
Shlens, Jon ;
Wojna, Zbigniew .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :2818-2826
[19]   Detection of Clinically Significant Prostate Cancer Using Magnetic Resonance Imaging-Ultrasound Fusion Targeted Biopsy: A Systematic Review [J].
Valerio, Massimo ;
Donaldson, Ian ;
Emberton, Mark ;
Ehdaie, Behfar ;
Hadaschik, Boris A. ;
Marks, Leonard S. ;
Mozer, Pierre ;
Rastinehad, Ardeshir R. ;
Ahmed, Hashim U. .
EUROPEAN UROLOGY, 2015, 68 (01) :8-19
[20]   Towards Personalized Statistical Deformable Model and Hybrid Point Matching for Robust MR-TRUS Registration [J].
Wang, Yi ;
Cheng, Jie-Zhi ;
Ni, Dong ;
Lin, Muqing ;
Qin, Jing ;
Luo, Xiongbiao ;
Xu, Ming ;
Xie, Xiaoyan ;
Heng, Pheng Ann .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2016, 35 (02) :589-604