Deformable Registration Algorithm via Non-subsampled Contourlet Transform and Saliency Map

doi:10.1007/s12204-022-2428-3

Abstract

Abstract: Medical image registration is widely used in image-guided therapy and image-guided surgery to esti- mate spatial correspondence between planning and treatment images. However, most methods based on intensity have the problems of matching ambiguity and ignoring the influence of weak correspondence areas on the overall registration. In this study, we propose a novel general-purpose registration algorithm based on free-form defor- mation by non-subsampled contourlet transform and saliency map, which can reduce the matching ambiguities and maintain the topological structure of weak correspondence areas. An optimization method based on Markov random fields is used to optimize the registration process. Experiments on four public datasets from brain, car- diac, and lung have demonstrated the general applicability and the accuracy of our algorithm compared with two state-of-the-art methods.

Key words: medical image registration, non-subsampled contourlet transform, saliency map, Markov random fields

CLC Number:

TP391

CHANG Qing∗ (常青), YANG Wenyou (杨文友), CHEN Lanlan (陈兰岚). Deformable Registration Algorithm via Non-subsampled Contourlet Transform and Saliency Map[J]. J Shanghai Jiaotong Univ Sci, 2022, 27(4): 452-462.

References 46

[1]	CAO Q, BROERSEN A, DE GRAAF M A, et al.Automatic identification of coronary tree anatomyin coronary computed tomography angiography [J].The International Journal of Cardiovascular Imaging,2017, 33(11): 1809-1819.
[2]	KHALIL A, NG S C, LIEW Y M, et al. An overviewon image registration techniques for cardiac diagnosisand treatment [J]. Cardiology Research and Practice,2018, 2018: 1437125.
[3]	GANSER K A, DICKHAUS H, METZNER R, et al.A deformable digital brain atlas system according toTalairach and Tournoux [J]. Medical Image Analysis,2004, 8(1): 3-22.
[4]	HU S, WEI L, GAO Y, et al. Learning-based de-formable image registration for infant MR images in the first year of life [J]. Medical Physics, 2017, 44(1):158-170.
[5]	ZITOV á B, FLUSSER J. Image registration methods: A survey [J]. Image and Vision Computing, 2003,21(11): 977-1000.
[6]	OLIVEIRA F P M, TA V ARES J M R S. Medical image registration: A review [J]. Computer Method sin Biomechanics and Biomedical Engineering, 2014,17(2): 73-93.
[7]	SMITH S M, BRADY J M. SUSAN: A new approach to low level image processing [J]. International Journal of Computer Vision, 1997, 23(1): 45-78.
[8]	LOWE D G. Distinctive image features from scale-invariant key points [J]. International Journal of Computer Vision , 2004, 60(2): 91-110.
[9]	LI Z, HUANG F, ZHANG J, et al. Multi-modal and multi-vendor retina image registration [J]. Biomedical Optics Express, 2018, 9(2): 410-422.
[10]	BAY H, ESS A, TUYTELAARS T, et al. Speeded-up robust features (SURF) [J]. Computer Vision and Image Understanding, 2008, 110(3): 346-359.
[11]	SANG Q, ZHANG J, YU Z. Robust non-rigid point registration based on feature-dependant finite mixture model [J]. Pattern Recognition Letters, 2013, 34(13):1557-1565.
[12]	XIANG Z, LI M, XIAO L, et al. Deformable registration of chest radiographs using B-spline based method with modified residual complexity [J]. Journal of Shanghai Jiao Tong University (Science), 2019,24(2): 226-232.
[13]	BROIT C. Optimal registration of deformed images[D]. Philadelphia, USA: University of Pennsylvania,1981.
[14]	SCHNABEL J A, TANNER C, CASTELLANO-SMITH A D, et al. Validation of nonrigid image registration using finite-element methods: Application to breast MR images [J]. IEEE Transactions on Medical Imaging, 2003, 22(2): 238-247.
[15]	THIRION J P. Image matching as a diffusion process:An analogy with Maxwell’s demons [J]. Medical Image Analysis, 1998, 2(3): 243-260.
[16]	W ANG C, REN Q, QIN X, et al. Adaptive diffeomorphic multiresolution demons and their application to same modality medical image registration with large deformation [J]. International Journal of Biomedical Imaging, 2018, 2018: 7314612.
[17]	CHAKRABORTY S, PRADHAN R, ASHOUR A S, et al. Grey-wolf-based Wang’s demons for retinal image registration [J]. Entropy, 2020, 22(6): 659.
[18]	LIAO S, CHUNG A C S. Non-rigid image registration with uniform spherical structure patterns[M]//Information processing in medical imaging.Berlin, Heidelberg: Springer, 2009: 163-175.
[19]	XUE Z, SHEN D, DA V ATZIKOS C. CLASSIC: Consistent longitudinal alignment and segmentation for se-rial image computing [J]. NeuroImage, 2006, 30(2):388-399.
[20]	WU G, QI F, SHEN D. Learning-based deformable registration of MR brain images [J]. IEEE Transactions on Medical Imaging, 2006, 25(9): 1145-1157.
[21]	MCEACHEN J C, DUNCAN J S. Shape-based tracking of left ventricular wall motion [J]. IEEE Transactions on Medical Imaging, 1997, 16(3): 270-283.
[22]	BHATNAGAR G, WU Q M J, LIU Z. Directive contrast based multimodal medical image fusion in NSCT domain [J]. IEEE Transactions on Multimedia, 2013,15(5): 1014-1024.
[23]	RUECKERT D, ALJABAR P, HECKEMANN R A,et al. Diffeomorphic registration using B-splines [M]//Medical image computing and computer-assisted intervention - MICCAI 2006. Berlin, Heidelberg: Springer,2006: 702-709.
[24]	CHOI Y, LEE S. Injectivity conditions of 2D and 3Duniform cubic B-spline functions [J]. Graphical Models,2000, 62(6): 411-427.
[25]	ASHBURNER J, FRISTON K J. Nonlinear spatial normalization using basis functions [J]. Human Brain Mapping, 1999, 7(4): 254-266.
[26]	RUECKERT D, SONODA L I, HAYES C, et al. Non-rigid registration using free-form deformations: Application to breast MR images [J]. IEEE Transactions on Medical Imaging, 1999, 18(8): 712-721.
[27]	AUER M, REGITNIG P, HOLZAPFEL G A. An automatic nonrigid registration for stained histologicalsections [J]. IEEE Transactions on Image Processing,2005, 14(4): 475-486.
[28]	SHEKHAR R, ZAGRODSKY V, GARCIA M J, et al. Registration of real-time 3-D ultrasound images of the heart for novel 3-D stress echocardiography [J]. IEEE Transactions on Medical Imaging, 2004, 23(9): 1141-1149.
[29]	KANG J T, ZHANG Y Z, QIN S Q. A hybrid evolutionary algorithm for identifying multiple alternativesin model updating [J]. Journal of Shanghai Jiao Tong University, 2020, 54(6): 652-660 (in Chinese).
[30]	LOECKX D, MAES F, V ANDERMEULEN D, et al.Temporal subtraction of thorax CR images using a statistical deformation model [J]. IEEE Transactions on Medical Imaging, 2003, 22(11): 1490-1504.
[31]	LI X Q, CHANG Q. A hybrid nonrigid medical image registration method on chest radiography [C]//202013th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics(CISP-BMEI ). Chengdu, China: IEEE, 2020: 651-657.
[32]	XIANG J, ZHANG J, W ANG B, et al. Low data over-lap rate graph-based SLAM with distributed submapstrategy [J]. Journal of Shanghai Jiao Tong University(Science), 2020, 25(5): 650-658.
[33]	ROTH S, LEMPITSKY V, ROTHER C. Discrete-continuous optimization for optical flow estimation[M]//Statistical and geometrical approaches to visual motion analysis. Berlin, Heidelberg: Springer, 2009:1-22.
[34]	ZIKIC D, GLOCKER B, KUTTER O, et al. Lin-ear intensity-based image registration by Markov random fields and discrete optimization [J]. Medical Image Analysis, 2010, 14(4): 550-562.
[35]	PORCHETTO R, STRAMANA F, PARAGIOS N, et al. Rigid slice-to-volume medical image registration through Markov random fields [C]//Medical computer vision and Bayesian and graphical models for biomed-ical imaging. Cham: Spring, 2017: 172-185.
[36]	KOMODAKIS N, TZIRITAS G, PARAGIOS N. Per-formance vs computational efficiency for optimizing single and dynamic MRFs: Setting the state of theart with primal-dual strategies [J]. Computer Visionand Image Understanding, 2008, 112(1): 14-29.
[37]	BOYKOV Y, VEKSLER O, ZABIH R. Fast approximate energy minimization via graph cuts [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(11): 1222-1239.
[38]	HEINRICH M P, JENKINSON M, BRADY M, et al.MRF-based deformable registration and ventilation estimation of lung CT [J]. IEEE Transactions on Medical Imaging, 2013, 32(7): 1239-1248.
[39]	BERNARD O, LALANDE A, ZOTTI C, et al. Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: Is the problem solved? [J]. IEEE Transactions on Medical Imaging,2018, 37(11): 2514-2525.
[40]	MUELLER S G, WEINER M W, THAL L J, et al.Ways toward an early diagnosis in Alzheimer’s dis-ease: The Alzheimer’s Disease Neuroimaging Initiative(ADNI) [J]. Alzheimer’s & Dement, 2005, 1(1): 55-66.
[41]	W ANG X, PENG Y, LU L, et al. ChestX-Ray8:Hospital-scale chest X-ray database and bench markson weakly-supervised classification and localization of common thorax diseases [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. H o nolulu, USA: IEEE, 2017: 3462-3471.
[42]	CASTILLO R, CASTILLO E, FUENTES D, et al.A reference dataset for deformable image registration spatial accuracy evaluation using the COPDgene study archive [J]. Physics in Medicine and Biology, 2013,58(9): 2861-2877.
[43]	W ANG H, DONG L, O’DANIEL J, et al. Validation of an accelerated ‘demons’ algorithm for deformable image registration in radiation therapy [J]. Physics in Medicine and Biology, 2005, 50(12): 2887-2905.
[44]	A V ANTS B B, EPSTEIN C L, GROSSMAN M, etal. Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain [J]. Medical Image Analysis, 2008, 12(1): 26-41.
[45]	KLEIN S, STARING M, MURPHY K, et al. Elastix:A toolbox for intensity-based medical image registration [J]. IEEE Transactions on Medical Imaging, 2010,29(1): 196-205.
[46]	A V ANTS B B, TUSTISON N J, SONG G, et al. A re-producible evaluation of ANTs similarity metric performance in brain image registration [J]. NeuroImage,2011, 54(3): 2033-2044.