Integrated Segmentation and Non-linear Registration for Organ Segmentation and Motion Field Estimation in 4D CT Data

Summary

Objectives: The development of spatiotemporal tomographic imaging techniques allows the application of novel techniques for diagnosis and therapy in the medical routine. However, in consequence to the increasing amount of image data automatic methods for segmentation and motion estimation are required. In adaptive radiation therapy, registration techniques are used for the estimation of respiration-induced motion of pre-segmented organs. In this paper, a variational approach for the simultaneous computation of segmentations and a dense non-linear registration of the 3D images of the sequence is presented.

Methods: In the presented approach, a variational region-based level set segmentation of the structures of interest is combined with a diffusive registration of the spatial images of the sequence. We integrate both parts by defining a new energy term, which allows us to incorporate mutual prior information in order to improve the segmentation as well as the registration quality.

Results: The presented approach was utilized for the segmentation of the liver and the simultaneous estimation of its respiration-induced motion based on four-dimensional thoracic CT images. For the considered patients, we were able to improve the results of the segmentation and the motion estimation, compared to the conventional uncoupled methods.

Conclusions: Applied in the field of radiation therapy of thoracic tumors, the presented integrated approach turns out to be useful for simultaneous segmentation and registration by improving the results compared to the application of the methods independently.

Keywords

Level set segmentation - variational registration - 4D-CT - computer-assisted image analysis - motion estimation

• References

• 1 Schweikard A, Glosser G, Bodduluri M, Murphy M, Adler JR. Robotic motion compensation for respiratory movement during radiosurgery.. Comput Aided Surg 2000; 5: 263-277.
• 2 Sarrut D, Boldea V, Ayadi M, Badel J, Ginestet C, Clippe S, Carrie C. Nonrigid registration method to assess reproducibility of breath-holding with ABC in lung cancer.. Int J Radiat Oncol Biol Phys 2005; 61 (Suppl. 02) 594-607.
• 3 Handels H, Werner R, Schmidt R, Frenzel T, Lu W, Low DA, Ehrhardt J. 4D medical image computing and visualization of lung tumor mobility in spatio-temporal CT image data.. Int J Med Inform 2007; 76 (Suppl. 03) S433-S439.
• 4 Werner R, Ehrhardt J, Frenzel T, Lu W, Low DA, Säring D, Handels H. Motion artifact reducing reconstruction of 4D CT image data for the analysis of respiratory dynamics.. Methods Inf Med 2007; 46 (Suppl. 03) 254-260.
• 5 Weruaga L, Morales J, Nunez L, Verdu R. Estimating volumetric motion in human thorax with parametric matching constraints.. IEEE Trans Med Imaging 2003; 22 (Suppl. 06) 766-772.
• 6 Rohlfing T, Maurer CR, O’Dell WG, Zhong J. Modeling liver motion and deformation during the respiratory cycle using intensity-based free-form registration of gated MR images.. In: Medical Imaging 2001 Visualisation, Display, and Image Guided Procedures. Proc SPIE; LNCS Vol 4319 337-348
• 7 Chen Y, Tagare HD, Thiruvenkadam S, Huang F, Wilson DC, Gopinath KS, Briggs RW, Geiser EA. Using Prior Shapes in Geometric Active Contours in a Variational Framework.. Int J Comput Vis 2002; 50 (Suppl. 03) 315-328.
• 8 Paragios N. A level set approach for shape-driven segmentation and tracking of the left ventricle.. IEEE Trans Med Imaging 2003; 22 (Suppl. 06) 773-776.
• 9 Yezzi A, Zollei L, Kapur T. A variational framework for integrating segmentation and registration through active contours.. Med Image Anal 2003; 7 (Suppl. 02) 171-185.
• 10 Young Y, Levy D. Registration-based morphing of active contours for segmentation of CT scans.. Math Biosci Eng 2005; 2 (Suppl. 01) 79-96.
• 11 Flach B, Schlesinger D. Unifying Registration and Segmentation for Multi-Sensor Images.. Pattern Recognit 2002; 2449: 190-197.
• 12 Wyatt P, Noble J. MAP MRF joint segmentation and registration of medical images.. Med Image Anal 2003; 7 (Suppl. 04) 539-552.
• 13 Pohl KM, Fisher J, Levitt JJ, Shenton ME, Kikinis R, Grimson WEL, Wells WM. A Unifying Approach to Registration, Segmentation, and Intensity Correction.. In: Proc MICCAI 2005 Vol 3749 310-318
• 14 Ashburner J, Friston K. Unified segmentation.. NeuroImage 2005; 26 (Suppl. 03) 839-851.
• 15 D’Agostino E, Maes F, Vandermeulen D, Suetens P. A Unified Framework for Atlas Based Brain Image Segmentation and Registration.. In: Proc WBIR 2006 LNCS Vol 4057 136-143
• 16 Xiaohua C, Brady M, Rueckert D. Simultaneous Segmentation and Registration for Medical Image.. In: Proc MICCAI 2004 LNCS Vol 3216 663-670
• 17 Cremers D, Soatto S. Variational space-time motion segmentation.. In: Proc VCBM 2003 Vol 2 886-893
• 18 An J, Chen Y, Huang F, Wilson DC, Geiser EA. A Variational PDE Based Level Set Method for a Simultaneous Segmentation and Non-rigid Registration.. In: Proc MICCAI 2005 LNCS Vol 3749 286-293
• 19 Karantzalos K, Paragios N. Implicit Free-Form-Deformations for Multi-frame Segmentation and Tracking.. In: Proc VLSM 2005 LNCS Vol 3752 217-282
• 20 Unal G, Slabaugh G. Coupled PDEs for nonrigid registration and segmentation.. IEEE Comput Soc Conf Comput Vis Pattern Recogn 2005; 1: 168-175.
• 21 Han J, Berkels B, Rumpf M, Hornegger J, Droske M. A Variational Framework for Joint Image Registration, Denoising and Edge Detection.. In: Proc BVM 2006 246-250
• 22 Sethian JA, Osher S. Level Set Methods and Fast Marching Methods.. Cambridge University Press: 1999
• 23 Chan TF, Vese L. Active contours without edges.. IEEE Trans Image Process 2001; 10 (Suppl. 02) 266-277.
• 24 Parzen E. On the estimation of a probability density function and mode.. Ann Math Stat 1962; 33: 1065-1076.
• 25 Zitova B, Flusser J. Image registration methods: a survey.. Image Vis Comput 2003; 21 (11) 977-1000.
• 26 Handels H, Horsch A, Meinzer H. Advances in Medical Image Computing.. Methods Inf Med 2007; 46 (Suppl. 03) 251-253.
• 27 Modersitzki J. Numerical Methods for Image Registration.. Oxford University Press: 2004
• 28 Sarrut D, Boldea V, Miguet S, Ginestet C. Simulation of four-dimensional CT images from deformable registration between inhale and exhale breath-hold CT scans.. Med Phys 2006; 33 (Suppl. 03) 605-617.
• 29 Whitaker RT. A Level-Set Approach to 3D Reconstruction from Range Data.. Int J Comput Vis 1998; 29 (Suppl. 03) 203-231.
• 30 Segars WP. Development and Application of the New Dynamic NURBS-based Cardiac-Torso (NCAT) Phantom.. PhD thesis University of North Carolina: 2001
• 31 Low DA, Nystrom M, Kalinin E, Parikh P, Dempsey JF, Bradley JD, Mutic S, Wahab SH, Islam T, Christensen G, Politte DG, Whiting BR. A method for the reconstruction of four-dimensional synchronized CT scans acquired during free breathing.. Med Phys 2003; 30 (Suppl. 06) 1254-1263.
• 32 Ehrhardt J, Werner R, Säring D, Lu W, Low DA, Handels H. An optical flow based method for improved reconstruction of 4D CT data sets acquired during free breathing.. Med Phys 2007; 34 (Suppl. 02) 711-21.
• 33 Ehrhardt J, Säring D, Handels H. Structure-preserving Interpolation of Temporal and Spatial Image Sequences Using an Optical Flow-based Method.. Methods Inf Med 2007; 46 (Suppl. 03) 300-307.
• 34 Säring D, Ehrhardt J, Stork A, Bansmann MP, Lund GK, Handels H. Computer-Assisted Analysis of 4D Cardiac MR Image Sequences after Myocardial Infarction.. Methods Inf Med 2006; 45: 377-383.