Abstract: X-ray images are projective, meaning that the 3D geometry is flattened along projection lines going from the source to the detector. In particular procedures, such as mapping or ablation, the interventional instrument lies on the wall of the organ. Using a 3D segmentation of this organ registered to the x-ray, the instrument necessarily lies on the intersection of this surface with its projection line. The line and the surface typically intersect with a segmentation surface at a discrete number of points (typically 2 for shapes such as the anterior of the LA). One then has just to disambiguate between these different possible locations to determine the exact location of the instrument. In this invention, we propose to use the apparent width of the instrument measured in x-ray images to accomplish this task.

Abstract: A system and method for toboggan-based object detection in cutting planes are provided. A method for detecting an object in an image includes: determining a region of interest (ROI) in the image; determining a toboggan potential for each image element in the ROI; extracting a plurality of cutting planes from the ROI; and performing a tobogganing in the cutting planes to form a toboggan cluster to determine a location of the object, wherein image elements inside the toboggan cluster are stored in a cluster-member list, image elements on an outer-border of the toboggan cluster are stored in an outer-border list and image elements on an inner-border of the toboggan cluster are stored in an inner-border list.

Abstract: A method of visualizing an object in an image includes presenting an image, selecting a point in an object of interest in said image, estimating a gradient of the image in a region about the selected point, calculating a structure tensor from the image gradient, analyzing said structure tensor to determine a main orientation of said object of interest, and presenting a visualization of said object of interest based on the main orientation of the object. Various techniques can be used to increase the robustness of the gradient estimation with respect to noise, and to enhance the visualization of the object-of-interest presented to a user.

Abstract: A method of storing a digital image in a computer memory includes providing a N-dimensional digital image, defining an offset for each image element (x1, . . . , xN) by the formula offset ? ( x 1 , … ? , x N ) = ? i ? ? n = 1 N ? K x n ? ( i ) ? x ni , where i is summed over all bits and n is summed over all dimensions. The coefficient K for the ith bit of the nth dimension is defined as K x n ? ( i ) = ( ? j = 1 n - 1 ? f ? ( x j , 2 i + 1 , sx j ) ) ? 2 i ? ( ? j = n + 1 N ? f ? ( x j , 2 i , sx j ) ) , where xj is the jth dimension, f(x,G,sxj)=min(G,sxj??x?G) G is a power of 2, sxj represents the size associated with a given dimension, and ?x?G=x?x mod G. Image elements are stored in the computer memory in an order defined by the offset of each image element.

Abstract: In one aspect of the present invention, a method for calculating a response value at a first voxel indicative of a global shape in an image is provided. The method includes the steps of (a) determining at least one local shape descriptor associated with each of the at least one local shape descriptor; (b) determining a spread function associated with the each of the at least one local shape descriptor; (c) determining second voxels around the first voxel; (d) calculating values for each the at least one local shape descriptor at each of the second voxels; (e) determining a contribution of each of the second voxels at the first voxel based on the spread functions; and (f) using a combination function to combine the contributions to determine the response value indicative of the global shape.

Abstract: An exemplary for selecting seeds from an image for region determination is provided. The method includes determining a boundary between two areas in the image; selecting pixels on the boundary that are characterized by a salient feature that identifies the pixels as seeds for determining a region; and determining a second region from one of the selected pixels if the one of the selected pixels is not part of a previously determined first region.

Abstract: A method of identifying a polyp in a digital image of a colon, wherein said image comprises a plurality of intensities corresponding to a domain of voxels in a 3-dimensional space, is provided. The method includes providing the image with a set of 3 mutually orthogonal axes, providing a plurality of cutting planes each at a different orientation with respect to the image axes, centering, for each voxel in the image, each of the cutting planes about a central voxel, determining, for each of the plurality of cutting planes about each voxel in the image, an intersection of the cutting plane with the colon, and examining a trace of the cutting plane within said intersection, and marking, where the trace of each cutting plane is small and round, those voxels in the intersection for further analysis.

Abstract: A method of identifying spherical objects in a digital image is provided, wherein the image includes a plurality of intensities corresponding to a domain of points in a D-dimensional space. The method includes calculating a local cross-correlation between a point in the domain of the image and a Gaussian kernel about a neighborhood of the point; calculating a local standard deviation of the point in the image; calculating a local standard deviation of the Gaussian kernel; calculating a cross-correlation ratio by dividing the local cross-correlation by the product of the local standard deviation of the image and the local standard deviation of the Gaussian kernel; and analyzing the cross-correlation ratio to determine whether an object about said point is spherical. The cross-correlation ratio can take continuous values from ?1 to 1, where a spherically symmetric Gaussian shaped object has a value of 1.

Abstract: A method of orienting a tubular structure in a digital image is provided, wherein the image comprises a plurality of intensities corresponding to a domain of points in a D-dimensional space. The method includes selecting a point in the domain of the image, computing, in a neighborhood of the selected point, a gradient of the image, computing an elementary structure tensor at the selected point, determining a structure tensor for the selected point, and finding the eigenvalues of the structure tensors. The eigenvector corresponding to the smallest eigenvalue is aligned with the tubular structure. A cartwheel projection can be calculated about an axis defined by the eigenvector that is aligned with the tubular structure.

Abstract: In one exemplary embodiment of the present invention, a method of detecting a desired object at a candidate pixel from an image is provided. The method includes the steps of (a) selecting a representative point in the desired object; (b) determining first representative cross-sections of the desired object by passing first lower dimension planes through the representative point; (c) passing at least one second lower dimension plane through the candidate pixel; (d) using region segmentation to separate the candidate pixel containing second regions from the rest of the pixels in each of the at least one second lower dimension plane; (e) matching at least one of the second regions with at least one of the first cross-sections; (f) determining a match value based on the result of step (e); and (g) using the match value to determine if the desired object is detected at the candidate pixel.

Abstract: A system and method for toboggan-based object detection in cutting planes are provided. A method for detecting an object in an image includes: determining a region of interest (ROI) in the image; determining a toboggan potential for each image element in the ROI; extracting a plurality of cutting planes from the ROI; and performing a tobogganing in the cutting planes to form a toboggan cluster to determine a location of the object, wherein image elements inside the toboggan cluster are stored in a cluster-member list, image elements on an outer-border of the toboggan cluster are stored in an outer-border list and image elements on an inner-border of the toboggan cluster are stored in an inner-border list.

Abstract: In one aspect of the present invention, a method for calculating a response value at a first voxel indicative of a global shape in an image is provided. The method includes the steps of (a) determining at least one local shape descriptor associated with each of the at least one local shape descriptor; (b) determining a spread function associated with the each of the at least one local shape descriptor; (c) determining second voxels around the first voxel; (d) calculating values for each the at least one local shape descriptor at each of the second voxels; (e) determining a contribution of each of the second voxels at the first voxel based on the spread functions; and (f) using a combination function to combine the contributions to determine the response value indicative of the global shape.

Abstract: A method of visualizing an object in an image includes presenting an image, selecting a point in an object of interest in said image, estimating a gradient of the image in a region about the selected point, calculating a structure tensor from the image gradient, analyzing said structure tensor to determine a main orientation of said object of interest, and presenting a visualization of said object of interest based on the main orientation of the object. Various techniques can be used to increase the robustness of the gradient estimation with respect to noise, and to enhance the visualization of the object-of-interest presented to a user.

Abstract: A method of visualizing an object in an image includes presenting an image, selecting a point in an object of interest in said image, determining a main orientation of said object of interest, presenting a first visualization of said object of interest, wherein said first visualization has a first display orientation characterized by the direction of a vector normal to the first visualization plane, and selecting a new point as a center of a new visualization and presenting said new visualization, wherein said new visualization has a new display orientation characterized by the direction of a vector normal to the new visualization plane.

Abstract: A method of storing a digital image in a computer memory includes providing a N-dimensional digital image, defining an offset for each image element (x1, . . . , xN) by the formula offset ? ( x 1 , … ? ? , x N ) = ? i ? ? ? ? n = 1 N ? ? ? K x n ? ( i ) ? x ni , where i is summed over all bits and n is summed over all dimensions. The coefficient K for the ith bit of the nth dimension is defined as K x n ? ( i ) = ( ? j = 1 n - 1 ? ? ? f ? ( x j , 2 i + 1 , sx j ) ) ? 2 i ? ( ? j = n + 1 N ? ? ? f ? ( x j , 2 i , sx j ) ) , where xj is the jth dimension, f(x,G,sxj)=min(G,sxj??x?G) G is a power of 2, sxj represents the size associated with a given dimension, and ?x?G=x?x mod G. Image elements are stored in the computer memory in an order defined by the offset of each image element.

Abstract: In one exemplary embodiment of the present invention, a method of detecting a desired object at a candidate pixel from an image is provided. The method includes the steps of (a) selecting a representative point in the desired object; (b) determining first representative cross-sections of the desired object by passing first lower dimension planes through the representative point; (c) passing at least one second lower dimension plane through the candidate pixel; (d) using region segmentation to separate the candidate pixel containing second regions from the rest of the pixels in each of the at least one second lower dimension plane; (e) matching at least one of the second regions with at least one of the first cross-sections; (f) determining a match value based on the result of step (e); and (g) using the match value to determine if the desired object is detected at the candidate pixel.

Abstract: An exemplary for selecting seeds from an image for region determination is provided. The method includes determining a boundary between two areas in the image; selecting pixels on the boundary that are characterized by a salient feature that identifies the pixels as seeds for determining a region; and determining a second region from one of the selected pixels if the one of the selected pixels is not part of a previously determined first region.

Abstract: A method of orienting a tubular structure in a digital image is provided, wherein the image comprises a plurality of intensities corresponding to a domain of points in a D-dimensional space. The method includes selecting a point in the domain of the image, computing, in a neighborhood of the selected point, a gradient of the image, computing an elementary structure tensor at the selected point, determining a structure tensor for the selected point, and finding the eigenvalues of the structure tensors. The eigenvector corresponding to the smallest eigenvalue is aligned with the tubular structure. A cartwheel projection can be calculated about an axis defined by the eigenvector that is aligned with the tubular structure.

Abstract: A method of identifying a polyp in a digital image of a colon, wherein said image comprises a plurality of intensities corresponding to a domain of voxels in a 3-dimensional space, is provided. The method includes providing the image with a set of 3 mutually orthogonal axes, providing a plurality of cutting planes each at a different orientation with respect to the image axes, centering, for each voxel in the image, each of the cutting planes about a central voxel, determining, for each of the plurality of cutting planes about each voxel in the image, an intersection of the cutting plane with the colon, and examining a trace of the cutting plane within said intersection, and marking, where the trace of each cutting plane is small and round, those voxels in the intersection for further analysis.

Abstract: A method of identifying spherical objects in a digital image is provided, wherein the image includes a plurality of intensities corresponding to a domain of points in a D-dimensional space. The method includes calculating a local cross-correlation between a point in the domain of the image and a Gaussian kernel about a neighborhood of the point; calculating a local standard deviation of the point in the image; calculating a local standard deviation of the Gaussian kernel; calculating a cross-correlation ratio by dividing the local cross-correlation by the product of the local standard deviation of the image and the local standard deviation of the Gaussian kernel; and analyzing the cross-correlation ratio to determine whether an object about said point is spherical. The cross-correlation ratio can take continuous values from ?1 to 1, where a spherically symmetric Gaussian shaped object has a value of 1.