Sorting 4DCT Images Using Locally Linear Embedding

Abstract:

Respiratory motion degrades anatomic position reproducibility, and result in significant errors in radiotherapy. 4D computed Tomography (4DCT) can characterize anatomy motion during breathing. Usually, the acquired 4DCT images sequences is out of order. How to rearrange the sequence, i.e. sort 4DCT images has been the focus of 4DCT. In this paper we propose a method based on locally linear embedding (LLE), to reconstruct time-resolved CT volumes. By mapping high dimensional image data with LLE into one dimensional space, each image is assigned a value, then 4DCT images is sorted according to the value to reconstruct a respiratory cycle. Experiments result shows that the method is feasible to sort 4 DCT images without using any external motion monitoring systems.

• Periodical: Applied Mechanics and Materials (Volumes 462-463)
• Pages: 150-154
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.462-463.150
• Online since: November 2013
• Authors: Zhao Hui Luo*, Zai Fang Xi
• Keywords: 4DCT, LLE, Respiratory Cycle

References

[1] P.F. Villard, M. Beuve, and B. Sharit, An Approach to Convert 4D Geometry into a 4D CT Scan, WSCG 2006 conference proceedings, Plzen, Czech Republic, January 30 - February 3, (2006).

[2] Nicole M. Wink, Christoph Panknin, and Timothy D. Solberg , "Phase versus amplitude sorting of 4D-CT data, JOURNAL OF APPLIED CLINICAL MEDICAL PHYSICS, VOLUME 7, NUMBER 1, WINTER 2006, pp.77-85.

DOI: 10.1120/jacmp.v7i1.2198

[3] Keall P. 4-dimensional computed tomography imaging and treatment planning. Semin Radiat Oncol. 2004; 14 (1): 81–90.

[4] Suresh Senan, and Frank J Lagerwaard, Current Status of Four-dimensional Computed Tomography for High-precision Radiotherapy, Radiotherapy & Imaging, T O U C H B R I E F I N G S 2 0 0 7, pp.98-101.

DOI: 10.17925/eoh.2007.0.1.88a

[5] Rietzel E, Pan T, Chen GT, Four-dimensional computed tomography: image formation and clinical protocol, Med Phys, 2005; 32: 874–89.

DOI: 10.1118/1.1869852

[6] Rongping Zeng, Jeffrey A. Fessler, James M. Balter, ITERATIVE SORTING FOR 4DCT IMAGES BASED ON INTERNAL ANATOMY MOTION, Biomedical Imaging: From Nano to Macro, 2007. ISBI 2007. 4th IEEE International Symposium on, pp.744-747.

DOI: 10.1109/isbi.2007.356959

[7] T. Pan, T-Y. Lee, E. Rietzel, and G. T. Y. Chen, 4D-CT imaging of a volume influenced by respiratory motion on multi-slice CT, Med. Phys., vol. 31, no. 2, Feb. 2004, pp.333-340.

DOI: 10.1118/1.1639993

[8] D. A. Low, M. Nystrom, E. Kalinin, P. Parikh, A method for the reconstruct of four-dimensional synchronized CT scans acquired during free breathing, Med. Phys. 30, 2003, pp.1254-1263.

DOI: 10.1118/1.1576230

[9] L. S. Johnson, S. W. Hadley, and C. A. Pelizzari, A video-based technique to gate radiotherapy treatments for respiration, Int. J. Radiat. Oncol., Biol., Phys. 42, 1998, pp.139-143.

DOI: 10.1016/s0360-3016(98)80131-4

[10] Kumar, S., Ramos, F.T., Upcroft, B. & Durrant-Whyte, H.F. A Statistical Framework for Natural Feature Representation， Proceedings of the IEEE/RSJ International Conference on Intelligent Robots & Systems, 2005 pp.1-6.

DOI: 10.1109/iros.2005.1544950

[11] Kajetan Berlinger, _Otto Sauer and Lucia Vences, A simple method for labeling CT images with respiratory states, Med. Phys. 33(9), September 2006, pp.3144-3148.

DOI: 10.1118/1.2229420

[12] Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000).

DOI: 10.1126/science.290.5500.2323

[13] A. Errity, J. McKenna, and B. Kirkpatrick, Manifold learning-based feature transformation for phone classification, in Proc. of the ISCA Tutorial and Research Workshop on Nonlinear Speech Processing (NOLISP), Paris, France, May 2007, pp.43-46.

DOI: 10.1007/978-3-540-77347-4_10