Abstract
Classical pairwise image registration methods search for a spatial transformation that optimises a numerical measure that indicates how well a pair of moving and fixed images are aligned. Current learning-based registration methods have adopted the same paradigm and typically predict, for any new input image pair, dense correspondences in the form of a dense displacement field or parameters of a spatial transformation model. However, in many applications of registration, the spatial transformation itself is only required to propagate points or regions of interest (ROIs). In such cases, detailed pixel- or voxel-level correspondence within or outside of these ROIs often have little clinical value. In this paper, we propose an alternative paradigm in which the location of corresponding image-specific ROIs, defined in one image, within another image is learnt. This results in replacing image registration by a conditional segmentation algorithm, which can build on typical image segmentation networks and their widely-adopted training strategies. Using the registration of 3D MRI and ultrasound images of the prostate as an example to demonstrate this new approach, we report a median target registration error (TRE) of 2.1 mm between the ground-truth ROIs defined on intraoperative ultrasound images and those propagated from the preoperative MR images. Significantly lower (>34%) TREs were obtained using the proposed conditional segmentation compared with those obtained from a previously-proposed spatial-transformation-predicting registration network trained with the same multiple ROI labels for individual image pairs. We conclude this work by using a quantitative bias-variance analysis to provide one explanation of the observed improvement in registration accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
DeTone, D., Malisiewicz, T., Rabinovich, A.: Deep image homography estimation. arXiv preprint arXiv:1606.03798 (2016)
de Vos, B.D., et al.: A deep learning framework for unsupervised affine and deformable image registration. Med. Image Anal. 52, 128–143 (2019)
Eppenhof, K.A., et al.: Deformable image registration using convolutional neural networks. In: Medical Imaging 2018: Image Processing, vol. 10574, p. 105740S (2018)
Rohé, M.-M., Datar, M., Heimann, T., Sermesant, M., Pennec, X.: SVF-Net: learning deformable image registration using shape matching. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.Louis, Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 266–274. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66182-7_31
Hu, Y., et al.: Weakly-supervised convolutional neural networks for multimodal image registration. Med. Image Anal. 49, 1–13 (2018)
Balakrishnan, G., et al.: VoxelMorph: a learning framework for deformable medical image registration. IEEE Trans. Med. Imaging 38, 1788–1800 (2019)
Hering, A., Kuckertz, S., Heldmann, S., Heinrich, M.P.: Enhancing label-driven deep deformable image registration with local distance metrics for state-of-the-art cardiac motion tracking. In: Handels, H., Deserno, T., Maier, A., Maier-Hein, K., Palm, C., Tolxdorff, T. (eds.) Bildverarbeitung für die Medizin 2019. I, pp. 309–314. Springer, Wiesbaden (2019). https://doi.org/10.1007/978-3-658-25326-4_69
Hu, Y., et al.: Adversarial deformation regularization for training image registration neural networks. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 774–782. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00928-1_87
Siddiqui, M.M., et al.: Comparison of MR/ultrasound fusion–guided biopsy with ultrasound-guided biopsy for the diagnosis of prostate cancer. JAMA 313(4), 390–397 (2015)
Valerio, M., et al.: New and established technology in focal ablation of the prostate: a systematic review. Eur. Urol. 71(1), 17–34 (2017)
Lawrence, S., et al.: Neural network classification and prior class probabilities. In: Neural Networks: Tricks of the Trade, pp. 299–313 (1998)
Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424–432. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_49
Webb, G.I.: Multiboosting: a technique for combining boosting and wagging. Mach. Learn. 40(2), 159–196 (2000)
Webb, G.I., Conilione, P.: Estimating bias and variance from data. Pre-publication manuscript (2005). http://users.monash.edu/~webb/Files/WebbConilione06.pdf
Gibson, E., et al.: NiftyNet: a deep-learning platform for medical imaging. Comput. Methods Programs Biomed. 158, 113–122 (2018)
Acknowledgement
This work is supported by the Wellcome/EPSRC Centre for Interventional and Surgical Sciences (203145Z/16/Z) and the Medical Image Analysis Network (EP/N026993/1). TV is supported by a Medtronic/RAEng Research Chair (RCSRF1819/7/34). Additional supports are from CRUK (C28070/A19985), the Wellcome (203145Z/16/Z; 203148/Z/16/Z) and the EPSRC (NS/A000050/1; NS/A000049/1).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Hu, Y., Gibson, E., Barratt, D.C., Emberton, M., Noble, J.A., Vercauteren, T. (2019). Conditional Segmentation in Lieu of Image Registration. In: Shen, D., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. MICCAI 2019. Lecture Notes in Computer Science(), vol 11765. Springer, Cham. https://doi.org/10.1007/978-3-030-32245-8_45
Download citation
DOI: https://doi.org/10.1007/978-3-030-32245-8_45
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32244-1
Online ISBN: 978-3-030-32245-8
eBook Packages: Computer ScienceComputer Science (R0)
