MOREA: a GPU-accelerated Evolutionary Algorithm for Multi-Objective Deformable Registration of 3D Medical Images
Pages 1294 - 1302
Abstract
Finding a realistic deformation that transforms one image into another, in case large deformations are required, is considered a key challenge in medical image analysis. Having a proper image registration approach to achieve this could unleash a number of applications requiring information to be transferred between images. Clinical adoption is currently hampered by many existing methods requiring extensive configuration effort before each use, or not being able to (realistically) capture large deformations. A recent multi-objective approach that uses the Multi-Objective Real-Valued Gene-pool Optimal Mixing Evolutionary Algorithm (MO-RV-GOMEA) and a dual-dynamic mesh transformation model has shown promise, exposing the trade-offs inherent to image registration problems and modeling large deformations in 2D. This work builds on this promise and introduces MOREA: the first evolutionary algorithm-based multi-objective approach to deformable registration of 3D images capable of tackling large deformations. MOREA includes a 3D biomechanical mesh model for physical plausibility and is fully GPU-accelerated. We compare MOREA to two state-of-the-art approaches on abdominal CT scans of 4 cervical cancer patients, with the latter two approaches configured for the best results per patient. Without requiring per-patient configuration, MOREA significantly outperforms these approaches on 3 of the 4 patients that represent the most difficult cases.
Supplementary Material
Supplemental material.
- Download
- 3.79 MB
References
[1]
T. Alderliesten, P. A. N. Bosman, and A. Bel. 2015. Getting the most out of additional guidance information in deformable image registration by leveraging multi-objective optimization. In SPIE Medical Imaging 2015: Image Processing. 94131R.
[2]
T. Alderliesten, J. J. Sonke, and P. A. N.Bosman. 2012. Multi-objective optimization for deformable image registration: proof of concept. In SPIE Medical Imaging 2012: Image Processing, Vol. 8314. 831420.
[3]
T. Alderliesten, J. J. Sonke, and P. A. N. Bosman. 2013. Deformable image registration by multi-objective optimization using a dual-dynamic transformation model to account for large anatomical differences. In SPIE Medical Imaging 2013: Image Processing, Vol. 8669. 866910.
[4]
G. Andreadis, P. A. N. Bosman, and T. Alderliesten. 2022. Multi-objective dual simplex-mesh based deformable image registration for 3D medical images - proof of concept. In SPIE Medical Imaging 2022: Image Processing. 744--750.
[5]
B. B. Avants, C. L. Epstein, M. Grossman, and J. C. Gee. 2008. Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain. Medical Image Analysis 12, 1 (2008), 26--41.
[6]
D. L. J. Barten, B. R. Pieters, A. Bouter, M. C. van der Meer, S. C. Maree, K. A. Hinnen, H. Westerveld, P. A. N. Bosman, T. Alderliesten, N. van Wieringen, and A. Bel. 2023. Towards artificial intelligence-based automated treatment planning in clinical practice: A prospective study of the first clinical experiences in high-dose-rate prostate brachytherapy. Brachytherapy In Press (2023).
[7]
L. Bondar, M. S. Hoogeman, E. M. Vásquez Osorio, and B. J.M. Heijmen. 2010. A symmetric nonrigid registration method to handle large organ deformations in cervical cancer patients. Medical Physics 37, 7 (2010), 3760--3772.
[8]
P. A. N. Bosman and T. Alderliesten. 2016. Smart grid initialization reduces the computational complexity of multi-objective image registration based on a dual-dynamic transformation model to account for large anatomical differences. In SPIE Medical Imaging 2016: Image Processing. 978447.
[9]
A. Bouter, T. Alderliesten, and P. A. N. Bosman. 2017. A novel model-based evolutionary algorithm for multi-objective deformable image registration with content mismatch and large deformations: benchmarking efficiency and quality. In SPIE Medical Imaging 2017: Image Processing, Vol. 10133. 1013312.
[10]
A. Bouter, T. Alderliesten, and P. A. N. Bosman. 2021. Achieving highly scalable evolutionary real-valued optimization by exploiting partial evaluations. Evolutionary Computation 29, 1 (2021), 129--155.
[11]
A. Bouter, T. Alderliesten, and P. A. N. Bosman. 2021. GPU-Accelerated Parallel Gene-pool Optimal Mixing applied to Multi-Objective Deformable Image Registration. In IEEE Congress on Evolutionary Computation. 2539--2548.
[12]
A. Bouter, T. Alderliesten, B. R. Pieters, A. Bel, Y. Niatsetski, and P. A. N. Bosman. 2019. GPU-accelerated bi-objective treatment planning for prostate high-dose-rate brachytherapy. Medical Physics 46, 9 (2019), 3776--3787.
[13]
A. Bouter, N. H. Luong, C. Witteveen, T. Alderliesten, and P. A. N. Bosman. 2017. The multi-objective real-valued gene-pool optimal mixing evolutionary algorithm. In Proceedings of the 2017 Genetic and Evolutionary Computation Conference. 537--544.
[14]
D. Brélaz. 1979. New methods to color the vertices of a graph. Commun. ACM 22, 4 (1979), 251--256.
[15]
K. K. Brock, S. Mutic, T. R. McNutt, H. Li, and M. L. Kessler. 2017. Use of image registration and fusion algorithms and techniques in radiotherapy: Report of the AAPM Radiation Therapy Committee Task Group No. 132: Report. Medical Physics 44, 7 (2017), e43--e76.
[16]
K. K. Brock, M. B. Sharpe, L. A. Dawson, S. M. Kim, and D. A. Jaffray. 2005. Accuracy of finite element model-based multi-organ deformable image registration. Medical Physics 32, 6 (2005), 1647--1659.
[17]
H. Chui and A. Rangarajan. 2000. A new algorithm for non-rigid point matching. In IEEE Conference on Computer Vision and Pattern Recognition. 44--51.
[18]
K. Deb. 2001. Multi-Objective Optimization using Evolutionary Algorithms. Wiley.
[19]
M. Faisal Beg, M. I. Miller, A. Trouvétrouv, and L. Younes. 2005. Computing Large Deformation Metric Mappings via Geodesic Flows of Diffeomorphisms. International Journal of Computer Vision 61, 2 (2005), 139--157.
[20]
B. Fischer and J. Modersitzki. 2008. Ill-posed medicine - An introduction to image registration. Inverse Problems 24, 3 (2008), 1--16.
[21]
J. Gascon, J. M. Espadero, A. G. Perez, R. Torres, and M. A. Otaduy. 2013. Fast deformation of volume data using tetrahedral mesh rasterization. In Proceedings - SCA 2013: 12th ACM SIGGRAPH / Eurographics Symposium on Computer Animation. 181--186.
[22]
S. Hang. 2015. TetGen, a Delaunay-Based Quality Tetrahedral Mesh Generator. ACM Trans. Math. Software 41, 2 (2015), 1--36.
[23]
F. Khalifa, G. M. Beache, G. Gimel'farb, J. S. Suri, and A. S. El-Baz. 2011. State-of-the-Art Medical Image Registration Methodologies: A Survey. In Multi Modality State-of-the-Art Medical Image Segmentation and Registration Methodologies. Springer, 235--280.
[24]
S. Klein, M. Staring, K. Murphy, M. A. Viergever, and J. P.W. Pluim. 2010. Elastix: A toolbox for intensity-based medical image registration. IEEE Transactions on Medical Imaging 29, 1 (2010), 196--205.
[25]
M. Li, E. Castillo, X. L. Zheng, H. Y. Luo, R. Castillo, Y. Wu, and T. Guerrero. 2013. Modeling lung deformation: A combined deformable image registration method with spatially varying Young's modulus estimates. Medical Physics 40, 8 (2013), 1--10.
[26]
G. Loi, M. Fusella, E. Lanzi, E. Cagni, C. Garibaldi, G. Iacoviello, F. Lucio, E. Menghi, R. Miceli, L. C. Orlandini, Antonella Roggio, Federica Rosica, Michele Stasi, Lidia Strigari, Silvia Strolin, and Christian Fiandra. 2018. Performance of commercially available deformable image registration platforms for contour propagation using patient-based computational phantoms: A multi-institutional study. Medical Physics 45, 2 (2018), 748--757.
[27]
H. N. Luong and P. A. N. Bosman. 2012. Elitist Archiving for Multi-Objective Evolutionary Algorithms: To Adapt or Not to Adapt. In Proceedings of the 12th Conference on Parallel Problem Solving from Nature. 72--81.
[28]
R. Mohammadi, S. R. Mahdavi, R. Jaberi, Z. Siavashpour, L. Janani, A. S. Meigooni, and R. Reiazi. 2019. Evaluation of deformable image registration algorithm for determination of accumulated dose for brachytherapy of cervical cancer patients. Journal of Contemporary Brachytherapy 11, 5 (2019), 469--478.
[29]
S. Nithiananthan, S. Schafer, D. J. Mirota, J. W. Stayman, W. Zbijewski, D. D. Reh, G. L. Gallia, and J. H. Siewerdsen. 2012. Extra-dimensional Demons: A method for incorporating missing tissue in deformable image registration. Medical Physics 39, 9 (2012), 5718--5731.
[30]
D. F. Pace, M. Niethammer, and S. R. Aylward. 2012. Sliding Geometries in Deformable Image Registration. In International MICCAI Workshop on Computational and Clinical Challenges in Abdominal Imaging. 141--148.
[31]
K. Pirpinia, P. A. N. Bosman, C. E. Loo, G. Winter-Warnars, N. N. Y. Janssen, A. N. Scholten, J. J. Sonke, M. van Herk, and T. Alderliesten. 2017. The feasibility of manual parameter tuning for deformable breast MR image registration from a multi-objective optimization perspective. Physics in Medicine and Biology 62, 14 (2017), 5723--5743.
[32]
B. Rigaud, A. Klopp, S. Vedam, A. Venkatesan, N. Taku, A. Simon, P. Haigron, R. De Crevoisier, K. K. Brock, and G. Cazoulat. 2019. Deformable image registration for dose mapping between external beam radiotherapy and brachytherapy images of cervical cancer. Physics in Medicine and Biology 64, 11 (2019), 115023.
[33]
L. Risser, F. X. Vialard, H. Y. Baluwala, and J. A. Schnabel. 2013. Piecewise-diffeomorphic image registration: Application to the motion estimation between 3D CT lung images with sliding conditions. Medical Image Analysis 17, 2 (2013), 182--193.
[34]
B. Schaly, J. A. Kempe, G. S. Bauman, J. J. Battista, and J. van Dyk. 2004. Tracking the dose distribution in radiation therapy by accounting for variable anatomy. Physics in Medicine and Biology 49, 5 (2004), 791--805.
[35]
A. Sotiras and N. Paragios. 2012. Deformable Image Registration: A Survey. Technical Report. Center for Visual Computing, Department of Applied Mathematics, Ecole Centrale de Paris, Equipe GALEN, INRIA Saclay.
[36]
D. Thierens and P. A. N. Bosman. 2011. Optimal mixing evolutionary algorithms. In Proceedings of the 2011 Genetic and Evolutionary Computation Conference. 617--624.
[37]
J.-P. Thirion. 1998. Image matching as a diffusion process: an analogy with Maxwell's Demons. Medical Image Analysis 2, 3 (1998), 243--260.
[38]
M. Unser, A. Aldroubi, and C. R. Gerfen. 1993. Multiresolution image registration procedure using spline pyramids. In SPIE Mathematical Imaging: Wavelet Applications in Signal and Image Processing, Vol. 2034. 160--170.
[39]
E. M. Vásquez Osorio, M. S. Hoogeman, L. Bondar, P. C. Levendag, and B. J. M. Heijmen. 2009. A novel flexible framework with automatic feature correspondence optimization for nonrigid registration in radiotherapy. Medical Physics 36, 7 (2009), 2848--2859.
[40]
O. Weistrand and S. Svensson. 2015. The ANACONDA algorithm for deformable image registration in radiotherapy. Medical Physics 42, 1 (2015), 40--53.
[41]
S. Wognum, L. Bondar, A. G. Zolnay, X. Chai, M. C. C. M. Hulshof, M. S. Hoogeman, and A. Bel. 2013. Control over structure-specific flexibility improves anatomical accuracy for point-based deformable registration in bladder cancer radiotherapy. Medical Physics 40, 2 (2013), 1--15.
[42]
H. Zhong, J. Kim, H. Li, T. Nurushev, B. Movsas, and I. J. Chetty. 2012. A finite element method to correct deformable image registration errors in low-contrast regions. Physics in Medicine and Biology 57, 11 (2012), 3499--3515.
Index Terms
- MOREA: a GPU-accelerated Evolutionary Algorithm for Multi-Objective Deformable Registration of 3D Medical Images
Recommendations
Diversifying Multi-Objective Gradient Techniques and their Role in Hybrid Multi-Objective Evolutionary Algorithms for Deformable Medical Image Registration
GECCO '15: Proceedings of the 2015 Annual Conference on Genetic and Evolutionary ComputationGradient methods and their value in single-objective, real-valued optimization are well-established. As such, they play a key role in tackling real-world, hard optimization problems such as deformable image registration (DIR). A key question is to which ...
Incremental gaussian model-building in multi-objective EDAs with an application to deformable image registration
GECCO '12: Proceedings of the 14th annual conference on Genetic and evolutionary computationEstimation-of-Distribution Algorithms (EDAs) build and use probabilistic models during optimization in order to automatically discover and use an optimization problems' structure. This is especially useful for black-box optimization where no assumptions ...
The multi-objective real-valued gene-pool optimal mixing evolutionary algorithm
GECCO '17: Proceedings of the Genetic and Evolutionary Computation ConferenceThe recently introduced Multi-Objective Gene-pool Optimal Mixing Evolutionary Algorithm (MO-GOMEA) exhibits excellent scalability in solving a wide range of challenging discrete multi-objective optimization problems. In this paper, we address ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
July 2023
1667 pages
Copyright © 2023 Owner/Author(s).
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike International 4.0 License.
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 12 July 2023
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- NWO
Conference
GECCO '23
Sponsor:
Acceptance Rates
Overall Acceptance Rate 1,669 of 4,410 submissions, 38%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 177Total Downloads
- Downloads (Last 12 months)130
- Downloads (Last 6 weeks)24
Reflects downloads up to 13 Nov 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in