臺灣博碩士論文加值系統

非剛體影像配準用來建立一組移動（moving）及模板（fixed）影像間，
像素對像素的對應關係，來對齊不同影向間的資訊，目前在醫學影像分析
上已經有廣泛的應用。傳統醫學影像配準技術，將這個目標視作最佳化問
題，透過重複迭代逐步求解，然而這個過程十分耗費時間與運算資源，也限
制了這項技術在實務上許多的應用。近期提出的方法，使用深度網路學習，
預先訓練一組用於影像配準的參數，直接預測將影像組配準所需的形變場
（deformation field)，大大縮短的計算所需的時間。然而，直接預測每個像
素的位移向量，可能會產生不可能在生物體中所產生的變形。因此這篇研
究，實現了類神經卷積網路的 B-spline 變換，來確保產生的變換場是平滑且
連續的，另外也提出 folding-free loss 來解決結果中折疊的情況發生。另外
透過多尺度學習，讓網路同時考慮不同尺度下的特徵，可以讓我們的方法在
ACDC 心臟 MRI 影像的配準準確度上，達到當前最優的結果。

Deformable image registration, which establishes a non-linear correspondence between a pair of images, is widly use a fundamental step in many medical image analysis procedures. Conventional registration methods, which
iteratively solve an optimization problem, can be very slow and hinder the
practical applications. To this end, formulating it as a learning based problem
using Convolutional Neural Networks (CNNs) can largely reduce the registration time [3]. Most of existing learning-based methods directly predict a
dense deformation field from an input pair of fixed and moving images. However, the resulting transformation could be physically implausible, and selffolding cannot be avoided. In this work, we model the deformation with Bspline transformation which intrinsically produces smooth deformation, and
the proposed local invertibility constraint largely alleviates the self-folding
issue in the resulting deformation field. We also present that our multi-scale
learning framework can further improve the registration accuracy. The proposed approach is trained in an unsupervised fashion, and no ground-truth
registration fields or landmark annotations are needed. Experimental results
demonstrate that our registration method outperforms current state-of-the-art
algorithms using public available ACDC cardiac cine MRI dataset [25].

誌謝 ii
摘要 iii
Abstract iv
1 Introduction 1
2 Background 4
2.1 DeformableImageRegistration....................... 4
2.2 B-splineTransformation .......................... 4
3 Related Works 7
3.1 Optimization-basedApproaches ...................... 7
3.2 SupervisedLearningApproaches...................... 7
3.3 UnsupervisedLearningApproaches .................... 8
4 Method 10
4.1 B-splineSpatialTransformer........................ 10
4.2 UnsupervisedLearningArchitecture.................... 10
4.3 Multi-scaletraining............................. 11
4.4 Learningtarget ............................... 11
4.5 Folding-freeconstraint ........................... 12
5 Experiments 14
5.1 Dataset ................................... 14
5.2 Evaluationmetric.............................. 14
5.3 BaselineMethod .............................. 15
5.4 Implementation ............................... 16
6 Results 17
7 Discussion 19
8 Conclusion 23
Bibliography 24

[1] V. Arsigny, O. Commowick, X. Pennec, and N. Ayache. A log-euclidean framework for statistics on diffeomorphisms. In Proc. MICCAI, pages 924–931, 2006.
[2] B. B. Avants, C. L. Epstein, M. Grossman, and J. C. Gee. Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain. Medical Image Analysis, 12(1):26–41, 2008.
[3] G. Balakrishnan, A. Zhao, M. R. Sabuncu, J. Guttag, and A. V. Dalca. An unsupervised learning model for deformable medical image registration. In Proc. CVPR, pages 9252–9260, 2018.
[4] M. F. Beg, M. I. Miller, A. Trouvé, and L. Younes. Computing large deformation metric mappings via geodesic flows of diffeomorphisms. IJCV, 61(2):139–157, 2005.
[5] B. D. de Vos, F. F. Berendsen, M. A. Viergever, M. Staring, and I. Išgum. End-to-end unsupervised deformable image registration with a convolutional neural network. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, pages 204–212. 2017.
[6] L. R. Dice. Measures of the amount of ecologic association between species. Ecology, 11(6):297–302, 1945.
[7] M. Jaderberg, K. Simonyan, A. Zisserman, et al. Spatial transformer networks. In Proc. NIPS, pages 2017–2025, 2015.
[8] P. Jiang and J. A. Shackleford. Cnn driven sparse multi-level b-spline image registration. In Proc. CVPR, June 2018.
[9] J. Kybic, P. Thévenaz, A. Nirkko, and M. Unser. Unwarping of unidirectionally distorted epi images. IEEE TMI, 19(2):80–93, 2000.
[10] S. Lee, G. Wolberg, K.-Y. Chwa, and S. Y. Shin. Image metamorphosis with scattered feature constraints. IEEE TVCG, 2(4):337–354, 1996.
[11] S. Lee, G. Wolberg, and S. Y. Shin. Scattered data interpolation with multilevel b-splines. IEEE TVCG, 3(3):228–244, 1997.
[12] H. Li and Y. Fan. Non-rigid image registration using self-supervised fully convolutional networks without training data. In Proc. ISBI), pages 1075–1078, 2018.
[13] J. Long, E. Shelhamer, and T. Darrell. Fully convolutional networks for semantic segmentation. In Proc. CVPR, pages 3431–3440, 2015.
[14] Y. Ou and C. Davatzikos. Dramms: deformable registration via attribute matching and mutual-saliency weighting. In Proc. IPMI, pages 50–62, 2009.
[15] Y. Ou, D. H. Ye, K. M. Pohl, and C. Davatzikos. Validation of dramms among 12 popular methods in cross-subject cardiac mri registration. In International Workshop on Biomedical Image Registration, pages 209–219, 2012.
[16] D. Rey, G. Subsol, H. Delingette, and N. Ayache. Automatic detection and segmentation of evolving processes in 3D medical images: Application to multiple sclerosis. Med Image Anal, 6(2):163–179, Jun 2002.
[17] M.-M. Rohé, M. Datar, T. Heimann, M. Sermesant, and X. Pennec. Svf-net: learning deformable image registration using shape matching. In Proc. MICCAI, pages 266–274, 2017.
[18] O. Ronneberger, P. Fischer, and T. Brox. U-net: convolutional networks for biomedical image segmentation. In Proc. MICCAI, pages 234–241, 2015.
[19] D. Rueckert, L. I. Sonoda, C. Hayes, D. L. Hill, M. O. Leach, and D. J. Hawkes. Nonrigid registration using free-form deformations: application to breast mr images. IEEE TMI, 18(8):712–721, 1999.
[20] D. Shen and C. Davatzikos. Hammer: hierarchical attribute matching mechanism for elastic registration. In Proc. IEEE Workshop on MMBIA, pages 29–36, 2001.
[21] H. Sokooti, B. de Vos, F. Berendsen, B. P. Lelieveldt, I. Išgum, and M. Staring. Nonrigid image registration using multi-scale 3d convolutional neural networks. In Proc. MICCAI, pages 232–239, 2017.
[22] J.-P. Thirion. Image matching as a diffusion process: an analogy with maxwell’s demons. Medical Image Analysis, 2(3):243–260, 1998.
[23] X. Yang, R. Kwitt, M. Styner, and M. Niethammer. Quicksilver: Fast predictive image registration–a deep learning approach. NeuroImage, 158:378–396, 2017.
[24] M. Zhang and P. T. Fletcher. Finite-dimensional lie algebras for fast diffeomorphic image registration. In Proc. IPMI, pages 249–260, 2015.
[25] X. Zhuang, L. Li, C. Payer, D. Štern, M. Urschler, M. P. Heinrich, J. Oster, C. Wang, O. Smedby, C. Bian, X. Yang, P.-A. Heng, A. Mortazi, U. Bagci, G. Yang, C. Sun, G. Galisot, J.-Y. Ramel, T. Brouard, and G. Yang. Evaluation of algorithms for multimodality whole heart segmentation: an open-access grand challenge. 02 2019.
[26] W. Zufeng, L. Tian, W. Jiang, D. Yi, and Q. Zhiguang. Medical image registration using b-spline transform. IJSSST, 17(48), 2016.