US 20100280365 A1 Abstract A method provides guidance to the physician during a live bronchoscopy or other endoscopic procedures. The 3D motion of the bronchoscope is estimated using a fast coarse tracking step followed by a fine registration step. The tracking is based on finding a set of corresponding feature points across a plurality of consecutive bronchoscopic video frames, then estimating for the new pose of the bronchoscope. In the preferred embodiment the pose estimation is based on linearization of the rotation matrix. By giving a set of corresponding points across the current bronchoscopic video image, and the CT-based virtual image as an input, the same method can also be used for manual registration. The fine registration step is preferably a gradient-based Gauss-Newton method that maximizes the correlation between the bronchoscopic video image and the CT-based virtual image. The continuous guidance is provided by estimating the 3D motion of the bronchoscope in a loop. Since depth-map information is available, tracking can be done by solving a 3D-2D pose estimation problem. A 3D-2D pose estimation problem is more constrained than a 2D-2D pose estimation problem and does not suffer from the limitations associated with computing an essential matrix. The use of correlation-based cost, instead of mutual information as a registration cost, makes it simpler to use gradient-based methods for registration.
Claims(32) 1. A video-based method for providing a pose estimate of an endoscope in conjunction with a live endoscopic procedure, the method comprising:
acquiring 3D image data of a target structure in advance of a live endoscopic procedure; receiving a frame of live endoscopic video image data including the target structure; and registering the frame of endoscopic video image data with acquired 3D image data to determine a pose estimate of the endoscope. 2. The method of 3. The method of 4. The method of 5. The method of 6. The method of 7. The method of 8. The method of a) estimating a three-dimensional location of the endoscope using (i) known motion information from said live endoscopic video image data, and (ii) local depth information obtained from the previously acquired 3D image data; and b) determining a new pose of the endoscope based on the 3D location estimated in step (a). 9. The method of 10. The method of 11. The method of (c) updating the previously acquired 3D image data in accordance with the new pose; and (d) repeating steps (a) through (c) until the guidance is terminated. 12. The method of 13. The method of 14. A video-based method for registering previously acquired 3D image data and live endoscopic video image data of a patient to obtain a current pose of an endoscope comprising:
a) performing an initial registration to register the previously acquired 3D image data and a frame of the live video image data to obtain a current pose and a current depth map; b) selecting a plurality of points associated with the live video image data; c) tracking the points over a plurality of consecutive frames to estimate the two-dimensional (2D) motion of the tracked points; d) deriving a three-dimensional (3D) motion of the endoscope using the 2D motion of the tracked points and the current depth map; e) determining a new pose based on the current depth map and 3D motion of the endoscope; and f) updating the current pose based upon the new pose. 15. The method of 16. The method of 17. A video-based method for providing a pose estimate of an endoscope in conjunction with a live endoscopic procedure, the method comprising:
receiving a frame of live endoscopic video image data of a target structure from the endoscope; and registering previously acquired 3D image data of the target structure and the frame of endoscopic video image data of the target structure to provide a pose estimate of the endoscope; and wherein the step of registering is performed using information arising from said frame of endoscopic video image data and the previously acquired 3D image data. 18. The method of 19. The method of 20. The method of 21. The method of 22. The method of 23. The method of 24. The method of a) estimating a three-dimensional location of the endoscope using (i) known motion information from said live endoscopic video image data, and (ii) local depth information obtained from the previously acquired 3D image data; and b) determining a new pose of the endoscope based on the 3D location estimated in step (a). 25. The method of 26. The method of 27. The method of (c) updating the previously acquired 3D image data in accordance with the new pose; and (d) repeating steps (a) through (c) until the guidance is terminated. 28. The method of 29. The method of 30. A video-based method for registering previously acquired 3D image data and live endoscopic video image data of a patient to obtain a current pose of an endoscope comprising:
g) performing an initial registration to register the previously acquired 3D image data and a frame of the live video image data to obtain a current pose and a current depth map; h) selecting a plurality of points associated with the live video image data; i) tracking the points over a plurality of consecutive frames to estimate the two-dimensional (2D) motion of the tracked points; j) deriving a three-dimensional (3D) motion of the endoscope using the 2D motion of the tracked points and the current depth map; k) determining a new pose based on the current depth map and 3D motion of the endoscope; and l) updating the current pose based upon the new pose. 31. The method of 32. The method of Description This application is a continuation of U.S. patent application Ser. No. 11/437,229, filed May 19, 2006, which claims priority to U.S. Provisional Patent Application Ser. No. 60/683,595, filed May 23, 2005, the entire content of each of which is incorporated herein by reference. This invention was made with government support under Grant No. R01 CA074325, awarded by the National Institutes of Health. The government has certain rights in the invention. This invention relates generally to bronchoscopy and, in particular, to a method that provides guidance to the physician during a live bronchoscopy or other applications. For lung cancer assessment, the physician needs to perform a biopsy of the suspect cancer sites, such as the peripheral nodules or mediastinal lymph nodes. Such sites are first identified by analyzing the 3D CT image data of the chest. Later, during bronchoscopy, the physician attempts to reach these sites with the help of the live video obtained from a bronchoscope. The success of a standard bronchoscopy depends heavily on the skill level and experience of the physician. The success of the bronchoscopy could be increased if the physician received some form of guidance during the procedure. Several guidance methods have been suggested in the past few years [1-5]. All of them use a CT-based (virtual) endoluminal rendering of the airway surface to obtain both the depth and visual data. They try to find the 3D location and orientation of the bronchoscope (pose) using the virtual renderings and incoming video frames. Bricault et al. proposed a method to register the bronchoscopic video (real) and 3D CT virtual bronchoscopic images [1]. The method uses the segmentation and shape from shading techniques to find the 3D surface for the real image and then does a 3D-3D registration of the computed surface with the virtual surface. Mori et al. proposed a method which first tracks a set of points across the real frames to estimate the bronchoscopic motion by computing the essential matrix and then does an estimation of the residual motion using image registration by Powell's method [3]. In [5], Mori et al. use a Kalman filter to predict bronchoscope motion and a new similarity measure to reduce the image area to be registered. Helferty et al. use a coarse tracking and fine registration approach [2,6]. The tracking is implemented by using the standard optical-flow constraint equation and depth-map information from the virtual rendering to estimate the motion parameters. The registration is done by maximizing the mutual information between the real and virtual image using the simplex method. The method proposed by Bricault et al. does not involve tracking and is limited to the bifurcation images [1]. The method of Mori et al. computes the essential matrix for tracking [3] and Powell's method for registration. The approach has three limitations. Firstly, the use of Powell's method makes the registration step slow. Secondly, the essential matrix cannot be determined if a subset of points are coplanar [7]. Thirdly, a translation can only be recovered up to a scale from the estimated essential matrix [7]. The optical-flow approach taken by Helferty et al. for tracking is slow since it involves iterative warping and computation of gradients for the images [2, 6]. Use of simplex method makes the registration step slow as well. This invention broadly resides in a system and method for providing guidance in conjunction with a diagnostic procedure. The method includes the steps of providing previously acquired image data of a body lumen, acquiring live image data of the body lumen, and registering the previously acquired image data and the live image data in real time or near real-time. In the preferred embodiment, the registration is used to guide an instrument such as an endoscope, bronchoscope, colonoscope or laparoscope. The previously acquired image data may be derived from virtual image data, including computerized tomographic (CT) slices. Alternatively, the previously acquired image data may be derived from a prerecorded video image. The live image data may be derived from video data acquired during the diagnostic procedure or from a stream of incoming virtual images. The invention has particular applicability to guidance during a live bronchoscopy. The 3D motion of the bronchoscope is estimated using a fast coarse tracking step followed by a fine registration step as necessary for correction purposes. The tracking is based on finding a set of corresponding feature points across a plurality of consecutive bronchoscopic video frames, then estimating for the new pose of the bronchoscope. In the preferred embodiment the pose estimation is based on linearization of the rotation matrix. By giving a set of corresponding points across the current bronchoscopic video image, and the CT-based virtual image as an input, the same method can also be used for manual registration. The fine registration step is a gradient-based Gauss-Newton method that maximizes the correlation-based cost between the bronchoscopic video image and the CT-based virtual image. The continuous guidance is provided by estimating the 3D motion of the bronchoscope in a loop. Since depth-map information is available, the tracking can be done by solving a 3D-2D pose estimation problem. A 3D-2D pose estimation problem is more constrained than a 2D-2D pose estimation problem and does not suffer from the limitations associated with computing an essential matrix. The use of correlation-based cost, instead of mutual information as a registration cost, makes it simpler to use gradient-based methods for registration. As discussed in the Summary of the Invention, to track the 3D motion of the bronchoscope, we use the fast coarse tracking and subsequent fine registration approach. We propose a 3D-2D pose estimation algorithm for tracking and a gradient-based Gauss-Newton method for registration which uses correlation-based cost as its cost function. It should be noted that even if the tracking algorithm is 100 percent accurate, one cannot avoid the fine registration step. This is because the 3D virtual surface data is not an accurate representation of the actual airway tree. The presence of the imaging artifacts, segmentation errors and issues related to lung capacity cause this. Hence, there will always be some drift errors during the tracking. If the drift errors are not taken care of by the registration step, they will accumulate to a point where tracking is no longer successful. In general the fine registration step takes more time. Accordingly, most of the motion should be estimated by a fast tracking method and the fine registration should only be done for correction. For tracking, we use correspondence of points between the real video frames along with the depth-map information from the virtual rendering to solve a 3D-2D pose estimation problem. Since the accumulated rotation is small over a small number of consecutive real frames, linearization of the rotation matrix can be done. Thus, the 3D-2D pose estimation problem reduces to solving a linear system of equations. The same method can be used for manual registration if the manual correspondence between the real and virtual image is given. For the fine registration step, we use the approach used for tracking by Helferty et al. [6]. This can be done by replacing the optical-flow constraint equation by a similar constraint based on correlation and replacing the source image with the virtual image. The second step is to choose a multiplicity of points from the current real frame I For fast coarse tracking of the bronchoscope, 20 feature points p Once a point is selected in image I
In (1), w is a Gaussian window function applied to get better centering or localization of a matched point, (u Since the camera motion is assumed to be small between the frames, a simple translational image motion model is used, as justified by Shi and Tomasi [8]. To accommodate larger motion, a Gaussian pyramid is constructed. The larger motion is estimated at a coarser level. This reduces the computation, since a smaller window P can be used for a template intensity patch and the search space S remains small at all the levels in the pyramid. Before tracking, feature points p The SSD of an image patch with itself as a function E(u
where (x,y) is varied over a patch P. For a small shift (u
is known as the autocorrelation matrix. This form of the autocorrelation matrix is valid only for a simple translational motion model. For other motion models—e.g., affine motion, the number of parameters and number of dimensions are large. The eigenvalues of the autocorrelation matrix have been used to analyze the local image structure and classify a feature as a corner or an edge [8, 10]. Zuliani et al. have analyzed the relationship between different detectors based on the eigenvalues of the autocorrelation matrix [11]. They give a criterion for feature-selection called the condition number. The condition number K where ε is a small number used for numerical stability. High value of a condition number means high sensitivity of the autocorrelation to the perturbations, which in turn means that the autocorrelation has a sharp peak at the point of interest. For implementation, around 60 points are short-listed as feature-point candidates based on the strength of the image gradient at that point. If depth Z After a feature point P Given the 3D locations W Many different classes of algorithms have been developed to solve this problem. Closed-form solutions exist for three or four points unless they are in a critical configuration [12-14]. These methods make use of the rigid geometrical constraints between the points to solve for a polynomial system of equations. For more than 4 points, one class of methods express a system of higher-order equations as a system of linear equations (over-dimensioning) to solve for depths first and then use the solution to absolute orientation problem to solve for the pose [15, 16]. Lu et al. give a fast iterative algorithm to determine the pose [17]. However, the method introduces large bias errors in the estimate of the translation when the object is very close to the camera or the depth of the object is comparable to the distance between the object and the camera, which holds true in our domain of application. Since the feature tracking is done over a few frames at a time, it can be assumed that the accumulated rotation is small. Our method uses this assumption to linearize the rotation matrix. Our method is very close to Lowe's method [18] and the least-squares adjustment step done by Haralick et al. [19]. A 3D rotation matrix R is given by
where θ, ψ and φ are the rotation angles around each axis. For small values of θ, ψ and φ, the rotation matrix can be written as
A 3D world point W transformed by (R, T) is given by:
The image of W′ through perspective projection is given by:
where f is the focal length. Henceforth, without loss of generality, f will be assumed to be 1. Given n world points (X
where (X
This gives an over-constrained system of linear equations:
The linear system of equations (15), can be solved using singular value decomposition (SVD), although care should be taken to make very small singular values equal to zero while solving. Since the linearized form (10) of R is an approximation, we have to a iterate few more times to reach the correct solution for (R,T). Using the current solution for (R,T), the 3D points W The method typically converges in 3 or 4 iterations. After the pose estimation step, the virtual image I Registration using Correspondence A fast way to register the two sources together is to use the same method as used for tracking. The only difference being that the correspondence will be found between the virtual image I Helferty et al. use the optical flow constraint equation along with the linearization of rotation matrix and the depth-map from the virtual image to do tracking [6]. We propose to use the same approach for fine registration of the virtual image I In the method given by Helferty et al., the goal is to register a real source image with a real target image by iteratively warping the source image towards the target image [6]. The 2D image motion of a point in the source image or optical flow (u
Its derivation is almost the same as given above. The optical flow constraint equation used to determine (u Using (17) and (18), a system of linear equations is set up to iteratively solve for (R, T). After each step, warping and computation of the gradients of the source image is done for the next iteration until convergence. The details can be found in [6]. In our case, the source image is I
The link to the Matlab code for the pose estimation method by Lu et al. is given in the paper [17]. After feature selection, tracking and pose estimation, the fine registration step is required to take care of the drift errors. The fine registration step can either be based on correspondence or on optical-flow. Fast tracking is an essential step in keeping the two sources together for guidance during bronchoscopy. It is not possible to escape from drift errors due to tracking, as they arise partially from small errors in the 3D image data. A fine registration step is then necessary to take care of drift errors. Feature-based 3D-2D pose estimation is a fast and stable technique to do tracking. It does not suffer from instability associated with computing an essential matrix. If correspondence is computed across both the real and virtual images, then this same set up can be used for registration as well. At least two other alternatives are available for guidance in the case of bronchoscopy. These alternatives include: -
- 1. The previously acquired image data is a prerecorded bronchoscopic video image sequence with associated depth information and the live source is incoming video from a bronchoscope.
- 2. The previously acquired image data is a prerecorded bronchoscopic video image sequence with associated depth information and the live source is a stream of incoming virtual images, as may be acquired when interactively navigating through a 3D CT image.
The application has far-reaching applications, particularly in the field of image-guided endoscopy. In summary, we disclose a new 3D-2D pose estimation method based on linearization of the rotation matrix. The method is iterative and has fast convergence in case of small rotation. Using normalized images in the optical-flow constraint equation makes it possible to use the gradient-based registration method by Helferty et al. for fine registration [6]. This approach is faster than using simplex method or Powell's method for registration.
- 1. I. Bricault, G. Ferretti, and P. Cinquin, “Registration of real and CT-derived virtual bronchoscopic images to assist transbronchial biopsy,” IEEE Transactions on Medical Imaging, Vol. 17, No. 5, pp. 703-714, October 1998.
- b
**2**. W. E. Higgins, J. P. Helferty, and D. R. Padfi, “Integrated bronchoscopic video tracking and 3D CT registration for virtual bronchoscopy,” SPIE Medical Imaging 2003: Physiology and Function: Methods, Systems, and Applications, A. Clough and A. Amini (eds) 5031, pp. 80-89, May 2003. - 3. K. Mori, D. Deguchi, J. Hasegawa, Y. Suenaga, J. Toriwaki, H. Takabatake, and H. Natori, “A method for tracking the camera motion of real endoscope by epipolar geometry analysis and virtual endoscopy system,” MICCAI '01: Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 1-8, 2001.
- 4. H. Shoji, K. Mori, J. Sugiyama, Y. Suenaga, J. Toriwaki, H. Takabatake, and H. Natori, “Camera motion tracking of real endoscope by using virtual endoscopy system and texture information,” SPIE Medical Imaging 2001: Physiology and Function from Multidimensional Images, Chin-Tu Chen and Anne V. Clough (eds) 4321, pp. 122-133, May 2001.
- 5. K. Mori, T. Enjoji, D. Deguchi, T. Kitasaka, Y. Suenaga, J. Toriwaki, H. Takabatake, and H. Natori, “New image similarity measures for bronchoscope tracking based on image registration between virtual and real bronchoscopic images,” SPIE Medical Imaging 2004: Physiology and Function from Multidimensional Images, Amir A. Amini and Armando Manduca (eds) 5369, pp. 165-176, April 2004.
- 6. J. P. Helferty and W. E. Higgins, “Combined endoscopic video tracking and virtual 3D CT registration for surgical guidance,” IEEE Int. Conference on Image Processing, pp. 11-961-11-964, September 2002.
- 7. R. I. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, ISBN: 0521623049, 2000.
- 8. J. Shi and C. Tomasi, “Good features to track,” IEEE Conf. Computer Vision and Pattern Recognition, pp. 593-600, June 1994.
- 9. B. Triggs, “Detecting keypoints with stable position, orientation and scale under illumination changes,” European Conference on Computer Vision, pp. IV 100-113, May 2004.
- 10. C. Harris and M. Stephens, “A combined corner and edge detector,” Alvey Vision Conference, pp. 147-151, 1988.
- 11. M. Zuliani, C. Kenney, and B. S. Manjunath, “A mathematical comparison of point detectors,” IEEE Image and Video Registration Workshop, June 2004.
- 12. M. Fischler and R. C. Bolles, “Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography,” Comm. ACM 24(6), pp. 381-395, 1981.
- 13. R. Horaud, B. Canio, and 0. Leboullenx, “An analytic solution for the perspective 4-point problem,” Computer Vision, Graphics, and Image Processing (1), pp. 33-44, 1989.
- 14. R. M. Haralick, C. Lee, K. Ottenberg, and M. Nolle, “Analysis and solutions of the three point perspective pose estimation problem,” Computer Vision and Pattern Recognition, pp. 592-598, 1991.
- 15. A. Ansar and K. Daniildis, “Linear pose estimation from points or lines,” IEEE Transactions on Pattern Analysis and Machine Intelligence 25, pp. 578-589, May 2003.
- 16. L. Quan and Z. Lan, “Linear n-point camera pose determination,” IEEE Transactions on Pattern Analysis and Machine Intelligence 21(8), pp. 774-780, 1999.
- 17. C. Lu, G. D. Hager, and E. Mjolsness, “Fast and globally convergent pose estimation from video images,” IEEE Transactions on Pattern Analysis and Machine Intelligence 22(6), pp. 610-622, 2000.
- 18. D. G. Lowe, “Fitting parametrized three-dimensional models to images,” IEEE Transactions on Pattern Analysis and Machine Intelligence 13(5), pp. 441-450, 1991.
- 19. R. M. Haralick, H. Joo, C. Lee, X. Zhuang, V. G. Vaidya, and M. B. Kim, “Analysis and solutions of the three point perspective pose estimation problem,” IEEE Transactions on Systems, Man, and Cybernetics 19(6), pp. 1426-1446, 1989.
Patent Citations
Referenced by
Classifications
Legal Events
Rotate |