Abstract
We present a novel 2D/3D deformable registration method, called Registration Efficiency and Accuracy through Learning Metric on Shape (REALMS), that can support real-time Image-Guided Radiation Therapy (IGRT). The method consists of two stages: planning-time learning and registration. In the planning-time learning, it firstly models the patient’s 3D deformation space from the patient’s time-varying 3D planning images using a low-dimensional parametrization. Secondly, it samples deformation parameters within the deformation space and generates corresponding simulated projection images from the deformed 3D image. Finally, it learns a Riemannian metric in the projection space for each deformation parameter. The learned distance metric forms a Gaussian kernel of a kernel regression that minimizes the leave-one-out regression residual of the corresponding deformation parameter. In the registration, REALMS interpolates the patient’s 3D deformation parameters using the kernel regression with the learned distance metrics. Our test results showed that REALMS can localize the tumor in 10.89 ms (91.82 fps) with 2.56±1.11 mm errors using a single projection image. These promising results show REALMS’s high potential to support real-time, accurate, and low-dose IGRT.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Russakoff, D.B., Rohlfing, T., Maurer, C.: Fast intensity-based 2D-3D image registration of clinical data using light fields. In: Proceedings of the Ninth IEEE International Conference on Computer Vision, vol. 1, pp. 416–422 (2003)
Russakoff, D.B., Rohlfing, T., Mori, K., Rueckert, D., Ho, A., Adler, J.R., Maurer, C.R.: Fast generation of digitally reconstructed radiographs using attenuation fields with application to 2d-3d image registration. IEEE Transactions on Medical Imaging 24, 1441–1454 (2005)
Khamene, A., Bloch, P., Wein, W., Svatos, M., Sauer, F.: Automatic registration of portal images and volumetric ct for patient positioning in radiation therapy. Medical Image Analysis 10, 96–112 (2006)
Munbodh, R., Jaffray, D.A., Moseley, D.J., Chen, Z., Knisely, J.P.S., Cathier, P., Duncan, J.S.: Automated 2d-3d registration of a radiograph and a cone beam ct using line-segment enhancement. Medical Physics 33, 1398–1411 (2006)
Li, R., Jia, X., Lewis, J.H., Gu, X., Folkerts, M., Men, C., Jiang, S.B.: Real-time volumetric image reconstruction and 3d tumor localization based on a single x-ray projection image for lung cancer radiotherapy. Medical Physics 37, 2822–2826 (2010)
Li, R., Lewis, J.H., Jia, X., Gu, X., Folkerts, M., Men, C., Song, W.Y., Jiang, S.B.: 3d tumor localization through real-time volumetric x-ray imaging for lung cancer radiotherapy. Medical Physics 38, 2783–2794 (2011)
Chou, C.R., Frederick, B., Chang, S., Pizer, S.: A Learning-Based patient repositioning method from Limited-Angle projections. In: Angeles, J., Boulet, B., Clark, J.J., Kövecses, J., Siddiqi, K. (eds.) Brain, Body and Machine. AISC, vol. 83, pp. 83–94. Springer, Heidelberg (2010)
Chou, C.R., Frederick, B., Liu, X., Mageras, G., Chang, S., Pizer, S.: Claret: A fast deformable registration method applied to lung radiation therapy. In: Fourth International (MICCAI) Workshop on Pulmonary Image Analysis, pp. 113–124 (2011)
Miao, S., Liao, R., Zheng, Y.: A hybrid method for 2-d/3-d registration between 3-d volumes and 2-d angiography for trans-catheter aortic valve implantation (tavi). In: ISBI, pp. 1215–1218 (2011)
Weinberger, K., Tesauro, G.: Metric learning for kernel regression. In: Eleventh International Conference on Artificial Intelligence and Statistics, pp. 608–615 (2007)
Lorenzen, P., Prastawa, M., Davis, B., Gerig, G., Bullitt, E., Joshi, S.: Multi-modal image set registration and atlas formation. Medical Image Analysis 10(3), 440–451 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chou, CR., Pizer, S. (2013). Real-Time 2D/3D Deformable Registration Using Metric Learning. In: Menze, B.H., Langs, G., Lu, L., Montillo, A., Tu, Z., Criminisi, A. (eds) Medical Computer Vision. Recognition Techniques and Applications in Medical Imaging. MCV 2012. Lecture Notes in Computer Science, vol 7766. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-36620-8_1
Download citation
DOI: https://doi.org/10.1007/978-3-642-36620-8_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-36619-2
Online ISBN: 978-3-642-36620-8
eBook Packages: Computer ScienceComputer Science (R0)