A Review on Medical Image Registration Techniques

This paper discusses the current trends in medical
image registration techniques and addresses the need to provide a
solid theoretical foundation for research endeavours. Methodological
analysis and synthesis of quality literature was done, providing a
platform for developing a good foundation for research study in
this field which is crucial in understanding the existing levels of
knowledge. Research on medical image registration techniques assists
clinical and medical practitioners in diagnosis of tumours and lesion
in anatomical organs, thereby enhancing fast and accurate curative
treatment of patients. Literature review aims to provide a solid
theoretical foundation for research endeavours in image registration
techniques. Developing a solid foundation for a research study is
possible through a methodological analysis and synthesis of existing
contributions. Out of these considerations, the aim of this paper is
to enhance the scientific community’s understanding of the current
status of research in medical image registration techniques and also
communicate to them, the contribution of this research in the field of
image processing. The gaps identified in current techniques can be
closed by use of artificial neural networks that form learning systems
designed to minimise error function. The paper also suggests several
areas of future research in the image registration.

Authors:

• Shadrack Mambo
• Karim Djouani
• Yskandar Hamam
• Barend van Wyk
• Patrick Siarry

Keywords:

• Image registration techniques
• medical images
• neural networks
• optimisation
• transformation.

References:

[1] Markelj P, Tomaˇzeviˇc D, Likar B and Pernuˇs F. A review of 3D/2D
registration methods for image-guided interventions. Medical image
analysis. 2012; 16(3):642–661.
[2] Fluck O, Vetter C, Wein W, Kamen A, Preim B and Westermann R. A
survey of medical image registration on graphics hardware. Computer
methods and programs in biomedicine. 2011; 104(3):e45–e57.
[3] Viergever Max A, Maintz JB, Antoine, Klein, Stefan, Murphy, Keelin,
Staring, Marius, Pluim and Josien PW. A survey of medical image
registration–under review. Medical Image Analysis. Elsevier; 2016;
33:140-144 .
[4] Oliveira FPM and Tavares JMRS. Medical image registration: a review.
Computer methods in biomechanics and biomedical engineering, Taylor
& Francis. 2014; 17(2):73–93.
[5] Sarrut D, Baudier T, Ayadi M, Tanguy R and Rit S. Deformable image
registration applied to lung SBRT: Usefulness and limitations. Physica
Medica: European Journal of Medical Physics, Elsevier; 2017; 44: p.
108–112.
[6] Zhou W and Xie Y. Interactive Multigrid refinement for deformable
image registration. BioMed research international, Hindawi Publishing
Corporation. 2013. [7] Gupta A, Verma HK and Gupta S. Technology and research developments
in carotid image registration. Biomedical Signal Processing and Control.
2012; 7(6):560–570.
[8] Sotiras Aristeidis, Davatzikos Christos and Paragios Nikos. Deformable
medical image registration: A survey. IEEE transactions on medical
imaging. IEEE; 2013; 32(7):1153–1190.
[9] Ezzeldeen RM, Ramadan HH, Nazmy TM, Yehia MA and Abdel WMS.
Comparative study for image registration techniques of remote sensing
images. The Egyptian Journal of Remote Sensing and Space Science.
Elsevier; 2010; 13(1):31–36.
[10] Cavoretto R, De Rossi A, Freda R, Qiao H and Venturino E.
Numerical Methods for Pulmonary Image Registration. arXiv preprint
arXiv:1705.06147, 2017.
[11] Van der Bom I, Klein S, Staring M, Homan R, Bartels L and Pluim
J. Evaluation of optimization methods for intensity-based 2D-3D
registration in x-ray guided interventions. In: SPIE Medical Imaging.
International Society for Optics and Photonics; 2011. p. 796223–796223.
[12] Song H and Qiu P. Intensity-based 3D local image registration. Pattern
Recognition Letters. Elsevier; 2017; 94:15–21.
[13] Wu G, Kim M, Wang Q, Gao Y, Liao S and Shen D. Unsupervised
deep feature learning for deformable registration of MR brain
images. International Conference on Medical Image Computing and
Computer-Assisted Intervention, Springer. 2013; p. 649–656.
[14] Toth D, Panayiotou M, Brost A, Behar JM, Rinaldi CA, Rhode
KS and Mountney P. 3D/2D Registration with superabundant vessel
reconstruction for cardiac resynchronization therapy. Medical image
analysis, Elsevier. 2017; 42:160–172.
[15] Wang J, Brown MS and Tan CL. Automatic corresponding control points
selection for historical document image registration. 10th International
Conference on Document Analysis and Recognition, IEEE. 2009; p.
1176–1180.
[16] Dung LR, Huang CM and Wu YY. Implementation of RANSAC
algorithm for feature-based image registration. Journal of Computer and
Communications, Scientific Research Publishing; 2013. 1(06):46, 2013.
[17] Hossein-nejad Z and Nasri M. Image registration based on SIFT features
and adaptive RANSAC transform. Communication and Signal Processing
(ICCSP), 2016 International Conference on; IEEE; 2014; 1087–1091.
[18] Zrour R, Kenmochi Y, Talbot H, Buzer L, Hamam Y, Shimizu I and
Sugimoto A. Optimal consensus set for digital line and plane fitting.
International Journal of Imaging Systems and Technology, Wiley Online
Library; 21(1):45–57, 2011.
[19] Hopp T, Dietzel M, Baltzer PA, Kreisel P, Kaiser WA and Gemmeke
H, et al. Automatic multimodal 2D/3D breast image registration using
biomechanical FEM models and intensity-based optimization. Medical
image analysis. 2013; 17(2):209–218.
[20] Klein S, Staring M, Murphy K, Viergever MA and Pluim JP. Elastix: a
toolbox for intensity-based medical image registration. Medical Imaging,
IEEE Transactions on. 2010; 29(1):196–205.
[21] Lu X, Ma H and Zhang B. A non-rigid medical image registration
method based on improved linear elastic model. Optik-International
Journal for Light and Electron Optics. 2012; 123(20):1867–1873.
[22] Bunting P, Labrosse F and Lucas R. A multi-resolution area-based
technique for automatic multi-modal image registration. Image and Vision
Computing. 2010; 28(8):1203–1219.
[23] Kosi´nski W, Michalak P and Gut P. Robust Image Registration Based
on Mutual Information Measure. Journal of Signal and Information
Processing. 2012; 3:175.
[24] Lin L, Jin C, Fu Z, Zhang B, Bin G and Wu S. Predicting healthy older
adult’s brain age based on structural connectivity networks using artificial
neural networks. Computer methods and programs in biomedicine. 2016;
125:8–17.
[25] Guo D, Qiu T, Bian J, Kang W and Zhang L. A computer-aided
diagnostic system to discriminate SPIO-enhanced magnetic resonance
hepatocellular carcinoma by a neural network classifier. Computerized
Medical Imaging and Graphics. 2009; 33(8):588–592.
[26] Schreibmann E, Thorndyke B, Li T, Wang J and Xing L.
Four-dimensional image registration for image-guided radiotherapy. In:
International Journal of Radiation Oncology, Biology and Physics.
Elsevier; 2008; 71(2): p. 578–586.
[27] Mezura-Montes E, Acosta-Mesa HG, Ram´ırez-Garc´es DS,
Cruz-Ram´ırez N and Hern´andez-Jim´enez R. An image registration
method for colposcopic images. Computational and mathematical
methods in medicine, Hindawi Publishing Corporation. 2013.
[28] Liu P, Eberhardt B, Wybranski C, Ricke J, and L¨udemann, L.
Nonrigid 3D medical image registration and fusion based on deformable
models. Computational and mathematical methods in medicine, Hindawi
Publishing Corporation. 2013.
[29] Rueckert D and Aljabar P. Nonrigid registration of medical images:
Theory, methods, and applications [applications corner]. Signal
Processing Magazine, IEEE. 2010; 27(4):113–119.
[30] Aktar N, Alam J and Pickering M. A non-rigid 3D multi-modal
registration algorithm using partial volume interpolation and the sum
of conditional variance. Digital lmage Computing: Techniques and
Applications (DlCTA), 2014 International Conference on, IEEE; p. 1–7,
2014.
[31] Zhang J, Chen L, Wang X, Teng Z, Brown AJ, Gillard JH, Guan Q and
Chen S. Compounding local invariant features and global deformable
geometry for medical image registration. PloS one. Public Library of
Science, 2014; 9(8):e105815.
[32] Kahaki SMM, Nordin MJ, Ashtari AH, and Zahra SJ. Invariant feature
matching for image registration application based on new dissimilarity
of spatial features. PloS one. Public Library of Science, 2016;
11(3):e0149710.
[33] Lu Y, Gao K, Zhang T and Xu T. A novel image registration approach
via combining local features and geometric invariants. PloS one. Public
Library of Science, 2018; 13(1):e0190383.
[34] Liu C, Ma J, Ma Y and Huang J. Retinal image registration via
feature-guided Gaussian mixture model. Journal of the Optical Society
of America A, Optical Society of America; 2016. 33(7):1267–1276.
[35] Li Z, Huang F, Zhang J, Dashtbozorg B, Abbasi-Sureshjani S, Sun
Y, Long X, Yu Q, ter Haar Romeny B and Tan T. Multi-modal
and multi-vendor retina image registration. Biomedical Optics Express,
Optical Society of America. 2018; (9)2:410–422.
[36] Ravikumar N, Gooya A, C¸ imen S, Frangi AF and Taylor ZA.
Group-wise similarity registration of point sets using Students t-mixture
model for statistical shape models. In: Medical image analysis, Elsevier;
2018; 44: p. 156–176.
[37] Ma J, Jiang J, Chen J, Liu C and Li C. Multimodal retinal image
registration using edge map and feature guided Gaussian mixture model.
Visual Communications and Image Processing (VCIP). IEEE; 2016. p.
1–4.
[38] Li Z, Mahapatra D, Tielbeek JAW, Stoker J, van Vliet LJ and Vos
FM. Image registration based on autocorrelation of local structure. IEEE
transactions on medical imaging, IEEE. 2016; 35(1):63–75.
[39] Zhong Z, Guo X, Cai Y, Yang Y, Wang J, Jia X and Mao W.
3D-2D Deformable Image Registration Using Feature-Based Nonuniform
Meshes. BioMed Research International, Hindawi; 2016.
[40] Esther Dura, Juan Domingo, Guillermo Ayala and Luis Mart´ı-Bonmat´ı.
Evaluation of the registration of temporal series of contrast-enhanced
perfusion magnetic resonance 3D images of the liver. Computer methods
and programs in biomedicine. Elsevier. 2012; 1083:932–945.
[41] Manjusha Deshmukh and Udhav Bhosle. A survey of image registration.
International Journal of Image Processing (IJIP), 5(3):245–269, 2011.
[42] Crum WR, Hartkens T and Hill D. Non-rigid image registration: theory
and practice. The British Journal of Radiology. 2014.
[43] Delibasis KK, Asvestas PA and Matsopoulos GK. Automatic point
correspondence using an artificial immune system optimization technique
for medical image registration. computerized medical imaging and
graphics. 2011; 35(1):31–41.
[44] Meskine F, Taleb N, El-Mezouar MC, Kpalma K and Almhdie A,
et al. A rigid point set registration of remote sensing images based on
genetic algorithms & Hausdorff distance. World Academy of Science,
Engineering and Technology. 2013; p. 1095–1100.
[45] Risser L, Vialard FX, Murgasova M, Holm D and Rueckert D. Large
deformation diffeomorphic registration using fine and coarse strategies.
In: Biomedical Image Registration. Springer; 2010. p. 186–197.
[46] Arguill`ere S, Miller M and Younes L. LDDMM Surface Registration
with Atrophy Constraints. arXiv preprint arXiv:150300765. 2015.
[47] Ceritoglu C, Wang L, Selemon LD, Csernansky JG, Miller MI and
Ratnanather JT. Large deformation diffeomorphic metric mapping
registration of reconstructed 3D histological section images and in vivo
MR images. Frontiers in human neuroscience. 2010; 4.
[48] Pai A, Sommer S, Darkner S, Sørensen L, Sporring J and Nielsen
M. Stepwise inverse consistent Eulers scheme for diffeomorphic image
registration. In: Biomedical Image Registration. Springer; 2014. p.
223–230.
[49] Lombaert H, Grady L, Pennec X, Peyrat JM, Ayache N and Cheriet F.
Groupwise spectral Log-Demons framework for atlas construction. In:
Medical Computer Vision. Recognition Techniques and Applications in
Medical Imaging. Springer; 2013. p. 11–19.
[50] Goshtasby AA. Image registration: Principles, tools and methods.
Springer Science & Business Media 2012. [51] Qiu Z, Tang H and Tian D. Non-rigid medical image registration based
on the thin-plate spline algorithm. Computer Science and Information
Engineering, 2009 WRI World Congress on, IEEE. 2009; 2. 522–527.
[52] Menon HP and Narayanankutty KA. Applicability of non-rigid medical
image registration using moving least squares. International Journal of
Computer Applications. 2010; 1(6): p. 79–86.
[53] Han X. Feature-constrained nonlinear registration of lung CT images.
Medical image analysis for the clinic: a grand challenge. 2010; p. 63–72.
[54] Klein S, Staring M and Pluim JPW. Evaluation of optimization
methods for nonrigid medical image registration using mutual information
and B-splines. IEEE transactions on image processing. 2007;
16(12):2879–2890.
[55] Yaegashi Yuji, Tateoka Kunihiko, Fujimoto Kazunori, Nakazawa
Takuya, Nakata Akihiro, Saito Yuichi, Abe Tadanori, Yano Masaki and
Sakata K. Assessment of similarity measures for accurate deformable
image registration. Journal of Nuclear medicine and Radiation Therapy.
Elsevier; 2012; 3(4).
[56] Glocker BM. Random fields for image registration. Technical University
Munich, 2011.
[57] Bernd Fischer and Jan Modersitzki. Ill-posed medicine-an introduction
to image registration. Inverse Problems, 24(3):034008, 2008.
[58] Dr´eo J, Nunes JC and Siarry P. Robust rigid registration of retinal
angiograms through optimization. Computerized Medical Imaging and
Graphics, Elsevier. 2006; 30(8):453–463.
[59] Dasgupta B, Divya K, Mehta VK and Deb K. RePAMO: Recursive
Perturbation Approach for Multimodal Optimization. Engineering
Optimization. 2013; 45(9):1073–1090.
[60] Chen C. Stochastic simulation optimization: an optimal computing
budget allocation. vol. 1. World scientific. 2010.
[61] de Groot M, Vernooij MW, Klein S, Ikram MA, Vos FM and Smith SM,
et al. Improving alignment in Tract-based spatial statistics: Evaluation and
optimization of image registration. NeuroImage. 2013; 76:400–411.
[62] Micha¨el Baudin, Vincent Couvert and Serge Steer. Optimization in
scilab. Technical report, Technical report, Scilab Consortium, July 2010.
http://forge. scilab. org/index. php/p/docoptimscilab, 2010.
[63] Klein S, Staring M, Andersson P and Pluim JP. Preconditioned stochastic
gradient descent optimisation for monomodal image registration. In:
Medical Image Computing and Computer-Assisted Intervention–MICCAI
2011. Springer; 2011. p. 549–556.
[64] Ralf Floca and Hartmut Dickhaus. A flexible registration and evaluation
engine (free). Computer methods and programs in biomedicine,
87(2):81–92, 2007.
[65] Stefan Klein. Optimisation methods for medical image registration. PhD
thesis, Image Sciences Institute, UMC Utrecht, 2008.
[66] Stefan Klein, Josien PW Pluim, Marius Staring and Max A Viergever.
Adaptive stochastic gradient descent optimisation for image registration.
International journal of computer vision, 81(3):227–239, 2009.
[67] Qiao Y, van Lew B, Lelieveldt BPF and Staring M. Fast automatic step
size estimation for gradient descent optimization of image registration.
IEEE transactions on medical imaging, IEEE; 35(2):391–403. 2016.
[68] Guo Y, Li J, Zhang P, Shao Q, Xu M and Li Y. Comparative evaluation of
target volumes defined by deformable and rigid registration of diagnostic
PET/CT to planning CT in primary esophageal cancer. Medicine, Wolters
Kluwer Health. 2017; 96(1): p e5528.
[69] Rigaud B, Simon A, Castelli J, Gobeli M, Ospina AJD, Cazoulat G,
Henry O, Haigron P and De Crevoisier R. Evaluation of deformable image
registration methods for dose monitoring in head and neck radiotherapy.
BioMed Research International, Hindawi; 2015.
[70] Wodzinski M, Skalski A, Ciepiela I, Kuszewski T, Kedzierawski P
and Gajda J. Improving oncoplastic breast tumor bed localization for
radiotherapy planning using image registration algorithms. Physics in
medicine and biology, IOP Publishing; 63(3). 2018.
[71] Setio AAA and others. Validation, comparison, and combination of
algorithms for automatic detection of pulmonary nodules in computed
tomography images: the LUNA16 challenge. Medical image analysis,
Elsevier; 42:1–13, 2017.
[72] Tang M and Chen F. A qualitative meta analysis review on medical
image registration evaluation. Procedia Engineering. Elsevier; 2012;
29:499–503 .
[73] Ou Y, Akbari H, Bilello M, Da X and Davatzikos C. Comparative
evaluation of registration algorithms in different brain databases with
varying difficulty: results and insights. IEEE transactions on medical
imaging. IEEE; 2014; 33(10):2039–2065.
[74] Werner R, Schmidt-Richberg A, Handels H and Ehrhardt J. Estimation
of lung motion fields in 4D CT data by variational non-linear
intensity-based registration: A comparison and evaluation study. Physics
in medicine and biology, IOP Publishing; 59(15): 4247. 2014.
[75] Razlighi QR, Kehtarnavaz N and Yousefi S. Evaluating similarity
measures for brain image registration. Journal of visual communication
and image representation, Elsevier; 24(7):977–987, 2013.
[76] Mahmoudzadeh AP and Kashou NH. Evaluation of interpolation effects
on upsampling and accuracy of cost functions-based optimized automatic
image registration. Journal of Biomedical Imaging, Hindawi Publishing
Corp.; 2013. p. 16. 2013.
[77] Kadoya N, Fujita Y, Katsuta Y and others. Evaluation of various
deformable image registration algorithms for thoracic images. Journal
of radiation research. Oxford University Press; 2014; 55(1):175–182.
[78] Shah SAA, Bennamoun M and Boussaid F. Performance evaluation of
3d local surface descriptors for low and high resolution range image
registration. Digital lmage Computing: Techniques and Applications
(DlCTA), 2014 International Conference on, IEEE; p. 1–7, 2014.