Markerless real-time 3-D target region tracking by motion backprojection from projection images

Accurate and fast localization of a predefined target region inside the patient is an important component of many image-guided therapy procedures. This problem is commonly solved by registration of intraoperative 2-D projection images to 3-D preoperative images. If the patient is not fixed during the intervention, the 2-D image acquisition is repeated several times during the procedure, and the registration problem can be cast instead as a 3-D tracking problem. To solve the 3-D problem, we propose in this paper to apply 2-D region tracking to first recover the components of the transformation that are in-plane to the projections. The 2-D motion estimates of all projections are backprojected into 3-D space, where they are then combined into a consistent estimate of the 3-D motion. We compare this method to intensity-based 2-D to 3-D registration and a combination of 2-D motion backprojection followed by a 2-D to 3-D registration stage. Using clinical data with a fiducial marker-based gold-standard transformation, we show that our method is capable of accurately tracking vertebral targets in 3-D from 2-D motion measured in X-ray projection images. Using a standard tracking algorithm (hyperplane tracking), tracking is achieved at video frame rates but fails relatively often (32% of all frames tracked with target registration error (TRE) better than 1.2 mm, 82% of all frames tracked with TRE better than 2.4 mm). With intensity-based 2-D to 2-D image registration using normalized mutual information (NMI) and pattern intensity (PI), accuracy and robustness are substantially improved. NMI tracked 82% of all frames in our data with TRE better than 1.2 mm and 96% of all frames with TRE better than 2.4 mm. This comes at the cost of a reduced frame rate, 1.7 s average processing time per frame and projection device. Results using PI were slightly more accurate, but required on average 5.4 s time per frame. These results are still substantially faster than 2-D to 3-D registration. We conclude that motion backprojection from 2-D motion tracking is an accurate and efficient method for tracking 3-D target motion, but tracking 2-D motion accurately and robustly remains a challenge.

[1]  Joachim Denzler,et al.  Progressive attenuation fields: Fast 2D‐3D image registration without precomputation , 2005 .

[2]  Achim Schweikard,et al.  Respiration tracking in radiosurgery. , 2004, Medical physics.

[3]  Graeme P. Penney,et al.  Standardized Evaluation of 2D-3D Registration , 2004, MICCAI.

[4]  Paul A. Viola,et al.  Alignment by Maximization of Mutual Information , 1997, International Journal of Computer Vision.

[5]  Margrit Betke,et al.  Real-Time 4D Tumor Tracking and Modeling from Internal and External Fiducials in Fluoroscopy , 2004, MICCAI.

[6]  F. A. Seiler,et al.  Numerical Recipes in C: The Art of Scientific Computing , 1989 .

[7]  D L Hill,et al.  Automated three-dimensional registration of magnetic resonance and positron emission tomography brain images by multiresolution optimization of voxel similarity measures. , 1997, Medical physics.

[8]  Calvin R. Maurer,et al.  A Linear Time Algorithm for Computing Exact Euclidean Distance Transforms of Binary Images in Arbitrary Dimensions , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  D. R. Fish,et al.  A patient-to-computed-tomography image registration method based on digitally reconstructed radiographs. , 1994, Medical physics.

[10]  A Hamadeh,et al.  Automated 3-dimensional computed tomographic and fluoroscopic image registration. , 1998, Computer aided surgery : official journal of the International Society for Computer Aided Surgery.

[11]  Takeo Kanade,et al.  Iterative x-ray/ct registration using accelerated volume rendering , 2001 .

[12]  Daniel Rueckert,et al.  Fast generation of digitally reconstructed radiographs using attenuation fields with application to 2D-3D image registration , 2005, IEEE Transactions on Medical Imaging.

[13]  Jay B. West,et al.  Predicting error in rigid-body point-based registration , 1998, IEEE Transactions on Medical Imaging.

[14]  Ramin Shahidi,et al.  Evaluation of Intensity-Based 2D-3D Spine Image Registration Using Clinical Gold-Standard Data , 2003, WBIR.

[15]  Jay B. West,et al.  Designing optically tracked instruments for image-guided surgery , 2004, IEEE Transactions on Medical Imaging.

[16]  Colin Studholme,et al.  An overlap invariant entropy measure of 3D medical image alignment , 1999, Pattern Recognit..

[17]  Guy Marchal,et al.  Multimodality image registration by maximization of mutual information , 1997, IEEE Transactions on Medical Imaging.

[18]  Nicholas Ayache,et al.  The Correlation Ratio as a New Similarity Measure for Multimodal Image Registration , 1998, MICCAI.

[19]  Jürgen Weese,et al.  A comparison of similarity measures for use in 2-D-3-D medical image registration , 1998, IEEE Transactions on Medical Imaging.

[20]  J Troccaz,et al.  Patient set-up using portal images: 2D/2D image registration using mutual information. , 2000, Computer aided surgery : official journal of the International Society for Computer Aided Surgery.

[21]  D L Hill,et al.  Validation of a two- to three-dimensional registration algorithm for aligning preoperative CT images and intraoperative fluoroscopy images. , 2001, Medical physics.

[22]  Tomaz Slivnik,et al.  3-D/2-D registration of CT and MR to X-ray images , 2003, IEEE Transactions on Medical Imaging.

[23]  C. Grassl,et al.  Efficient hyperplane tracking by intelligent region selection , 2004, 6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004..

[24]  Michel Dhome,et al.  Hyperplane Approximation for Template Matching , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Martin J Murphy,et al.  Tracking moving organs in real time. , 2004, Seminars in radiation oncology.

[26]  Wolfgang Birkfellner,et al.  A faster method for 3D/2D medical image registration—a simulation study , 2003, Physics in medicine and biology.

[27]  Joachim Denzler,et al.  Information Theoretic Sensor Data Selection for Active Object Recognition and State Estimation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Heinrich Niemann,et al.  Illumination Insensitive Template Matching with Hyperplanes , 2003, DAGM-Symposium.

[29]  Daniel Rueckert,et al.  Fast calculation of digitally reconstructed radiographs using light fields , 2003, SPIE Medical Imaging.

[30]  Jürgen Weese,et al.  Voxel-based 2-D/3-D registration of fluoroscopy images and CT scans for image-guided surgery , 1997, IEEE Transactions on Information Technology in Biomedicine.

[31]  Jocelyne Troccaz,et al.  Patient Set-Up Using Portal Images: 2D/2D Image Registration Using Mutual Information , 2000 .

[32]  Jürgen Weese,et al.  An approach to 2D/3D registration of a vertebra in 2D X-ray fluoroscopies with 3D CT images , 1997, CVRMed.

[33]  Arie E. Kaufman,et al.  Fast Ray-Tracing of Rectilinear Volume Data Using Distance Transforms , 2000, IEEE Trans. Vis. Comput. Graph..

[34]  David Sarrut,et al.  Geometrical Transformation Approximation for 2D/3D Intensity-Based Registration of Portal Images and CT Scan , 2001, MICCAI.

[35]  Jean-Claude Latombe,et al.  Image-Guided Robotic Radiosurgery , 1994, Modelling and Planning for Sensor Based Intelligent Robot Systems.

[36]  Kensaku Mori,et al.  Fast software-based volume rendering using multimedia instructions on PC platforms and its application to virtual endoscopy , 2003, SPIE Medical Imaging.

[37]  L. Joskowicz,et al.  Gradient-based 2-D/3-D rigid registration of fluoroscopic X-ray to CT , 2003, IEEE Transactions on Medical Imaging.

[38]  Gregory D. Hager,et al.  Efficient Region Tracking With Parametric Models of Geometry and Illumination , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[39]  Daniel B. Russakoff,et al.  Intensity-based 2D-3D spine image registration incorporating a single fiducial marker. , 2005, Academic radiology.

[40]  Joachim Denzler,et al.  Markerless Real-Time Target Region Tracking: Application to Frameless Sterotactic Radiosurgery , 2004, VMV.