I delarbete II exkluderades några bilder ur atlas på grund av dåliga registreringsre-sultat. Helkroppsregistrering är en svår utmaning då man måste ha en metod som klarar av alla variationer i människans anatomi. Delarbete IV syftade till att presentera två förbättringar till registreringsramverket; en förbättrad strategi för att uppdatera transformationen i varje iteration och ett nytt reg-ulariseringsmått som tillåter användaren att justera regulariseringen för olika vävnader. Dessa nya tillägg blev utvärderade tillsammans med den metod som använts i tidigare arbete i hopp om att kunna förbättra senare analyser. Något som har visat stor potential i många bildanalysapplikationer, inklusive bildreg-istrering, är användningen av metoder baserat på inlärning och djupa neurala nätverk. För att blicka framåt och bedömma hurvida metoder som dessa kan ersätta de traditionella metoder så utvärderas även VoxelMorph, ett ramverk för lärningsbaserad bildregistrering, på samma uppgift; helkroppsregistrering.
Acknowledgements
The work that led to this thesis was carried out at the Department of Surgical Sciences, Section of Radiology. I have met a number of great people during my doctoral studies and I would like to thank anyone who has inspired or supported me. Special thanks to:
My main supervisor, Robin Strand, for giving me an enormous support, inspiration, and guidance throughout my work. You have always seem to find the time for discussion and I am very grateful for the support that you have provided as I was writing this thesis.
My co-supervisor, Filip Malmberg, for never turning down the opportunity to discuss interesting challenges in image registration. I also really want to thank you for helping me kickstart my work by providing a captivating intro-duction to the field of image registration.
My co-supervisor, Joel Kullberg, for the great support and discussions. You have joined me in discussions on everything from how to write articles to possibly ground-breaking innovations.
My co-supervisor, Håkan Ahlström, for providing valuable feedback and medical expertise in an office full of engineers.
My colleagues at Entrance 24: Therese Sjöholm, Elin Lundström, Jonathan Andersson, Taro Lagner, Robin Visvanathar, Martino Pilia for the much needed coffee breaks, valuable discussions, and general support. I would like to es-pecially thank Therese Sjöholm for the collaboration on Paper II and Martino for the discussions and the many hours you have put in, helping me improve the registration software.
My colleages at Antaros Medical for being so welcoming and understand-ing of me not beunderstand-ing able to be at two places at the same time. I would like to especially thank Marcus Wilander Björk and Carl Sjöberg for the great dis-cussions on image registration and software developement which has been a great aid during my doctoral studies.
Mathias Engström for his incredibly pedagogical approach for describing the physics of MRI.
I am very grateful for the support and encouragement that I have received from my parents, Björn and Christina. Dad, you told me to never become an M.D. so I had to aim for "medicine doktor" instead.
I also want to thank the rest of my family and my friends for the encour-agement and support. A special thanks to the support that I have received by my girlfriend, especially during the hectic last weeks before submitting this thesis.
References
[1] Guha Balakrishnan, Amy Zhao, Mert R Sabuncu, John Guttag, and Adrian V Dalca. Voxelmorph: a learning framework for deformable medical image registration. IEEE transactions on medical imaging, 38(8):1788–1800, 2019.
[2] Johan Berglund, Lars Johansson, Håkan Ahlström, and Joel Kullberg.
Three-point dixon method enables whole-body water and fat imaging of obese subjects. Magnetic Resonance in Medicine: An Official Journal of the
International Society for Magnetic Resonance in Medicine, 63(6):1659–1668, 2010.
[3] Julian Besag. On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society: Series B (Methodological), 48(3):259–279, 1986.
[4] Yuri Boykov. Fast Approximate Energy Minimization via Graph Cuts. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 23(11):18, 2001.
[5] Yuri Boykov and Gareth Funka-Lea. Graph cuts and efficient nd image segmentation. International journal of computer vision, 70(2):109–131, 2006.
[6] Yuri Boykov and Vladimir Kolmogorov. An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision. 26(9):34, 2004.
[7] Lisa Gottesfeld Brown. A survey of image registration techniques. ACM Computing Surveys, 24(4):325–376, December 1992.
[8] B. V. Cherkassky and A. V. Goldberg. On Implementing the Push—Relabel Method for the Maximum Flow Problem. Algorithmica, 19(4):390–410, December 1997.
[9] Gary E Christensen, Xiujuan Geng, Jon G Kuhl, Joel Bruss, Thomas J Grabowski, Imran A Pirwani, Michael W Vannier, John S Allen, and Hanna Damasio. Introduction to the non-rigid image registration evaluation project (nirep). In International workshop on biomedical image registration, pages 128–135. Springer, 2006.
[10] G.E. Christensen and H.J. Johnson. Consistent image registration. IEEE Transactions on Medical Imaging, 20(7):568–582, July 2001.
[11] Keh-Shih Chuang, Hong-Long Tzeng, Sharon Chen, Jay Wu, and Tzong-Jer Chen. Fuzzy c-means clustering with spatial information for image
segmentation. computerized medical imaging and graphics, 30(1):9–15, 2006.
[12] Dan Claudiu Cire¸san, Ueli Meier, Luca Maria Gambardella, and Jürgen Schmidhuber. Deep, big, simple neural nets for handwritten digit recognition.
Neural computation, 22(12):3207–3220, 2010.
[13] Klev Diamanti, Robin Visvanathar, Maria J Pereira, Marco Cavalli, Gang Pan, Chanchal Kumar, Stanko Skrtic, Ulf Risérus, Jan W Eriksson, Joel Kullberg, et al. Integration of whole-body [18 f] fdg pet/mri with non-targeted
metabolomics can provide new insights on tissue-specific insulin resistance in type 2 diabetes. Scientific Reports, 10(1):1–9, 2020.
[14] Jack Edmonds and Richard M Karp. Theoretical improvements in algorithmic efficiency for network flow problems. Journal of the ACM (JACM),
19(2):248–264, 1972.
[15] Anders Eklund, Paul Dufort, Daniel Forsberg, and Stephen M. LaConte.
Medical image processing on the GPU – Past, present and future. Medical Image Analysis, 17(8):1073–1094, December 2013.
[16] Nathan D. Ellingwood, Youbing Yin, Matthew Smith, and Ching-Long Lin.
Efficient methods for implementation of multi-level nonrigid mass-preserving image registration on GPUs and multi-threaded CPUs. Computer Methods and Programs in Biomedicine, 127:290–300, April 2016.
[17] O. Fluck, C. Vetter, W. Wein, A. Kamen, B. Preim, and R. Westermann. A survey of medical image registration on graphics hardware. Computer Methods and Programs in Biomedicine, 104(3):e45–e57, December 2011.
[18] L. R. Ford and D. R. Fulkerson. Maximal Flow through a Network. Canadian Journal of Mathematics, 8:399–404, 1956.
[19] Lester Randolph Ford Jr and Delbert Ray Fulkerson. Flows in networks.
Princeton university press, 1962.
[20] Ben Glocker, Nikos Komodakis, Georgios Tziritas, Nassir Navab, and Nikos Paragios. Dense image registration through MRFs and efficient linear programming. Medical Image Analysis, 12(6):731–741, December 2008.
[21] Ben Glocker, Aristeidis Sotiras, Nikos Komodakis, and Nikos Paragios.
Deformable Medical Image Registration: Setting the State of the Art with Discrete Methods. Annual Review of Biomedical Engineering, 13(1):219–244, August 2011.
[22] Andrew V Goldberg and Robert E Tarjan. A new approach to the
maximum-flow problem. Journal of the ACM (JACM), 35(4):921–940, 1988.
[23] Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Yoshua Bengio. Deep learning, volume 1. MIT press Cambridge, 2016.
[24] Chris Gregg and Kim Hazelwood. Where is the data? Why you cannot debate CPU vs. GPU performance without the answer. In (IEEE ISPASS) IEEE INTERNATIONAL SYMPOSIUM ON PERFORMANCE ANALYSIS OF SYSTEMS AND SOFTWARE, pages 134–144, Austin, TX, USA, April 2011.
IEEE.
[25] D. M. Greig, B. T. Porteous, and A. H. Seheult. Exact Maximum A Posteriori Estimation for Binary Images. Journal of the Royal Statistical Society: Series B (Methodological), 51(2):271–279, January 1989.
[26] Xuejun Gu, Hubert Pan, Yun Liang, Richard Castillo, Deshan Yang, Dongju Choi, Edward Castillo, Amitava Majumdar, Thomas Guerrero, and Steve B Jiang. Implementation and evaluation of various demons deformable image registration algorithms on a GPU. Physics in Medicine and Biology, 55(1):207–219, January 2010.
[27] P Guglielmo, Simon Ekström, Robin Strand, Robin Visvanathar, Filip
Malmberg, Emil Johansson, MJ Pereira, S Skrtic, BCL Carlsson, JW Eriksson, et al. Validation of automated whole-body analysis of metabolic and
morphological parameters from an integrated fdg-pet/mri acquisition. Scientific reports, 10(1):1–8, 2020.
[28] Yanming Guo, Yu Liu, Theodoros Georgiou, and Michael S Lew. A review of
semantic segmentation using deep neural networks. International journal of multimedia information retrieval, 7(2):87–93, 2018.
[29] Grant Haskins, Uwe Kruger, and Pingkun Yan. Deep learning in medical image registration: a survey. Machine Vision and Applications, 31(1):8, 2020.
[30] Mohammad Havaei, Axel Davy, David Warde-Farley, Antoine Biard, Aaron Courville, Yoshua Bengio, Chris Pal, Pierre-Marc Jodoin, and Hugo Larochelle.
Brain tumor segmentation with deep neural networks. Medical image analysis, 35:18–31, 2017.
[31] Mattias P Heinrich, Mark Jenkinson, Michael Brady, and Julia A Schnabel.
Mrf-based deformable registration and ventilation estimation of lung ct. IEEE transactions on medical imaging, 32(7):1239–1248, 2013.
[32] M. Holden. A Review of Geometric Transformations for Nonrigid Body Registration. IEEE Transactions on Medical Imaging, 27(1):111–128, January 2008.
[33] Juan Eugenio Iglesias and Mert R. Sabuncu. Multi-atlas segmentation of biomedical images: A survey. Medical Image Analysis, 24(1):205–219, August 2015.
[34] T. Kalaiselvi, P. Sriramakrishnan, and K. Somasundaram. Survey of using GPU CUDA programming model in medical image analysis. Informatics in Medicine Unlocked, 9:133–144, 2017.
[35] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
[36] S. Klein, M. Staring, K. Murphy, M.A. Viergever, and J. Pluim. elastix: A Toolbox for Intensity-Based Medical Image Registration. IEEE Transactions on Medical Imaging, 29(1):196–205, January 2010.
[37] Stefan Klein, Marius Staring, Keelin Murphy, Max A Viergever, and Josien PW Pluim. Elastix: a toolbox for intensity-based medical image registration. IEEE transactions on medical imaging, 29(1):196–205, 2009.
[38] Vladimir Kolmogorov. What Energy Functions Can Be Minimized via Graph Cuts? IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 26(2):13, 2004.
[39] Joel Kullberg, Håkan Ahlström, Lars Johansson, and Hans Frimmel. Automated and reproducible segmentation of visceral and subcutaneous adipose tissue from abdominal mri. International journal of obesity, 31(12):1806–1817, 2007.
[40] Hava Lester and Simon R Arridge. A survey of hierarchical non-linear medical image registration. Pattern recognition, 32(1):129–149, 1999.
[41] S. Z. Li. Markov random field modeling in image analysis. Advances in pattern recognition. Springer, London, 3rd ed edition, 2009. OCLC: ocn262720244.
[42] Lars Lind, Robin Strand, Karl Michaëlsson, Håkan Ahlström, and Joel Kullberg.
Voxel-wise study of cohort associations in whole-body mri: Application in metabolic syndrome and its components. Radiology, 294(3):559–567, 2020.
[43] Lars Lind, Robin Strand, Karl Michaelsson, Joel Kullberg, and Håkan Ahlström. Relationship between endothelium-dependent vasodilation and fat distribution using the new “imiomics” image analysis technique. Nutrition, Metabolism and Cardiovascular Diseases, 29(10):1077 – 1086, 2019.
[44] Geert Litjens, Thijs Kooi, Babak Ehteshami Bejnordi, Arnaud Arindra Adiyoso Setio, Francesco Ciompi, Mohsen Ghafoorian, Jeroen Awm Van Der Laak,
Bram Van Ginneken, and Clara I Sánchez. A survey on deep learning in medical image analysis. Medical image analysis, 42:60–88, 2017.
[45] Jonathan Long, Evan Shelhamer, and Trevor Darrell. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3431–3440, 2015.
[46] JB Antoine Maintz and Max A Viergever. A survey of medical image registration. Medical image analysis, 2(1):1–36, 1998.
[47] Warren S McCulloch and Walter Pitts. A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5(4):115–133, 1943.
[48] Tim McInerney and Demetri Terzopoulos. Deformable models in medical image analysis: a survey. Medical image analysis, 1(2):91–108, 1996.
[49] Pinar Muyan-Ozcelik, John D. Owens, Junyi Xia, and Sanjiv S. Samant. Fast Deformable Registration on the GPU: A CUDA Implementation of Demons. In 2008 International Conference on Computational Sciences and Its Applications, pages 223–233, Perugia, Italy, June 2008. IEEE.
[50] Martino Pilia, Joel Kullberg, Håkan Ahlström, Filip Malmberg, Simon Ekström, and Robin Strand. Average volume reference space for large scale registration of whole-body magnetic resonance images. PLoS One, 14(10):e0222700, 2019.
[51] J.P.W. Pluim, J.B.A. Maintz, and M.A. Viergever. Mutual-information-based registration of medical images: a survey. IEEE Transactions on Medical Imaging, 22(8):986–1004, August 2003.
[52] Rajat Raina, Anand Madhavan, and Andrew Y Ng. Large-scale deep unsupervised learning using graphics processors. In Proceedings of the 26th annual international conference on machine learning, pages 873–880, 2009.
[53] Torsten Rohlfing. Image similarity and tissue overlaps as surrogates for image registration accuracy: widely used but unreliable. IEEE transactions on medical imaging, 31(2):153–163, 2011.
[54] Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241.
Springer, 2015.
[55] Frank Rosenblatt. The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review, 65(6):386, 1958.
[56] Daniel Rueckert, Luke I Sonoda, Carmel Hayes, Derek LG Hill, Martin O Leach, and David J Hawkes. Nonrigid registration using free-form
deformations: application to breast mr images. IEEE transactions on medical imaging, 18(8):712–721, 1999.
[57] Jason Sanders and Edward Kandrot. CUDA by example: an introduction to general-purpose GPU programming. Addison-Wesley, Upper Saddle River, NJ, 2011.
[58] Denis Shamonin. Fast parallel image registration on CPU and GPU for diagnostic classification of Alzheimer’s disease. Frontiers in Neuroinformatics, 7, 2013.
[59] Ramtin Shams, Parastoo Sadeghi, Rodney Kennedy, and Richard Hartley. A Survey of Medical Image Registration on Multicore and the GPU. IEEE Signal Processing Magazine, 27(2):50–60, March 2010.
[60] Erik Smistad, Thomas L. Falch, Mohammadmehdi Bozorgi, Anne C. Elster, and Frank Lindseth. Medical image segmentation on GPUs – A comprehensive review. Medical Image Analysis, 20(1):1–18, February 2015.
[61] Ronald W.K. So, Tommy W.H. Tang, and Albert C.S. Chung. Non-rigid image registration of brain magnetic resonance images using graph-cuts. Pattern Recognition, 44(10-11):2450–2467, October 2011.
[62] A. Sotiras, C. Davatzikos, and N. Paragios. Deformable Medical Image Registration: A Survey. IEEE Transactions on Medical Imaging, 32(7):1153–1190, July 2013.
[63] Robin Strand, Simon Ekström, Eva Breznik, Therese Sjöholm, Martino Pilia, Lars Lind, Filip Malmberg, Håkan Ahlström, and Joel Kullberg. Recent Advances in Large Scale Whole Body MRI Image Analysis - Imiomics. In 2020 International Conference on Sustainable Information Engineering and
Technology (SIET). ACM, November 2020.
[64] Robin Strand, Filip Malmberg, Lars Johansson, Lars Lind, Magnus Sundbom, Håkan Ahlström, and Joel Kullberg. A concept for holistic whole body MRI data analysis, Imiomics. PLOS ONE, 12(2):e0169966, February 2017.
[65] Ching-Lung Su, Po-Yu Chen, Chun-Chieh Lan, Long-Sheng Huang, and Kuo-Hsuan Wu. Overview and comparison of opencl and cuda technology for gpgpu. In 2012 IEEE Asia Pacific Conference on Circuits and Systems, pages 448–451. IEEE, 2012.
[66] Cathie Sudlow, John Gallacher, Naomi Allen, Valerie Beral, Paul Burton, John Danesh, Paul Downey, Paul Elliott, Jane Green, Martin Landray, Bette Liu, Paul Matthews, Giok Ong, Jill Pell, Alan Silman, Alan Young, Tim Sprosen, Tim Peakman, and Rory Collins. UK Biobank: An Open Access Resource for Identifying the Causes of a Wide Range of Complex Diseases of Middle and Old Age. PLOS Medicine, 12(3):e1001779, March 2015.
[67] Adam Szmul, Bartłomiej W. Papie˙z, Andre Hallack, Vicente Grau, and Julia A.
Schnabel. Supervoxels for graph cuts-based deformable image registration using guided image filtering. Journal of Electronic Imaging, 26(06):1, October 2017.
[68] Tommy W. H. Tang and Albert C. S. Chung. Non-rigid Image Registration Using Graph-cuts. In Nicholas Ayache, Sébastien Ourselin, and Anthony Maeder, editors, Medical Image Computing and Computer-Assisted
Intervention – MICCAI 2007, volume 4791, pages 916–924. Springer Berlin Heidelberg, Berlin, Heidelberg, 2007.
[69] J.-P. Thirion. Image matching as a diffusion process: an analogy with Maxwell’s demons. Medical Image Analysis, 2(3):243–260, September 1998.
[70] Yi Peng, Li Chen, Fang-Xin Ou-Yang, Wei Chen, and Jun-Hai Yong. JF-Cut: A Parallel Graph Cut Approach for Large-Scale Image and Video. IEEE
Transactions on Image Processing, 24(2):655–666, February 2015.
[71] Barbara Zitová and Jan Flusser. Image registration methods: a survey. Image and Vision Computing, 21(11):977–1000, October 2003.
Acta Universitatis Upsaliensis
Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Medicine 1687
Editor: The Dean of the Faculty of Medicine
A doctoral dissertation from the Faculty of Medicine, Uppsala University, is usually a summary of a number of papers. A few copies of the complete dissertation are kept at major Swedish research libraries, while the summary alone is distributed internationally through the series Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Medicine. (Prior to January, 2005, the series was published under the title “Comprehensive Summaries of Uppsala Dissertations from the Faculty of Medicine”.)
Distribution: publications.uu.se
UNIVERSITATISACTA UPSALIENSIS
UPPSALA