Abstract: A method for rib suppression in a chest x-ray image detects and labels one or more ribs in a region of interest and detects rib edges of the one or more detected ribs. Cross rib profiles are generated along the detected ribs. The original x-ray image is conditioned according to at least one of the detected rib edge and cross rib profiles. The conditioned x-ray image can be stored, displayed, or transmitted.

Abstract: A method for segmenting a feature of interest from a volume image acquires image data elements from the image of a subject. At least one view of the acquired volume is displayed. One or more boundary points along a boundary of the feature of interest are identified according to one or more geometric primitives defined by a user with reference to the displayed view. A foreground seed curve defined according to the one or more identified boundary points and a background seed curve encompassing and spaced apart from the foreground seed curve are formed. Segmentation is applied to the volume image according to foreground values that are spatially bounded within the foreground seed curve and according to background values that lie outside the background seed curve. An image of the segmented feature of interest is displayed.

Abstract: A method of generating a dissection curve between a first and a second object in a volume image. The method accesses volume image data of a subject as a set of image slices and identifies a region of the volume image data that includes at least the first and second objects. At least one starting point in the volume image data is defined for the dissection curve according to a geometric primitive entered by an operator. Successive dissection curve points are identified according to points of minimum intensity in successive image slices. The dissection curve that connects the identified plurality of successive dissection curve points is displayed.

Abstract: A method for forming a panoramic image from a computed tomography image volume, acquires image data elements for one or more computed tomographic volume images of a subject, identifies a subset of the acquired computed tomographic images that contain one or more features of interest and defines, from the subset of the acquired computed tomographic images, a sub-volume having a curved shape that includes one or more of the contained features of interest. The curved shape is unfolded by defining a set of unfold lines wherein each unfold line extends at least between two curved surfaces of the curved shape sub-volume and re-aligning the image data elements within the curved shape sub-volume according to a re-alignment of the unfold lines. One or more views of the unfolded sub-volume are displayed.

Abstract: A method for segmenting a feature of interest from a volume image acquires image data elements from the image of a subject. One or more boundary points along a boundary of the feature of interest are identified according to one or more geometric primitives with reference to the displayed view. A foreground seed curve is defined according to the one or more identified boundary points. A background field array that lies outside of, and is spaced from, the foreground seed curve by a predetermined distance, is defined. Segmentation is applied to the volume image according to foreground values obtained according to image data elements that are spatially bounded on or within the foreground seed curve and according to background field array values to create a segmented feature of interest.

Abstract: A method for processing digital volume image data, executed at least in part on a computer that has an associated graphics processing unit, orders the digital volume image data as a stack of two-dimensional image slices of voxels. A 1:1 mapping of each of the slices is formed, in sequential order, to a corresponding tile in a digital one-row flat volume in a global memory. For each voxel in the digital flat volume, a neighborhood is defined that has, relative to each voxel, four or more adjacent voxels that are within the corresponding tile of each voxel, and one or more adjacent voxels that are within the preceding tile, and one or more adjacent voxels that are within the next tile. Each voxel is updated according to information stored for the adjacent voxels in the defined neighborhood for said each voxel to form a rendered volume image, which is displayed.

Abstract: A method for processing a digital volume image receives the volume image formed as a stack of image slices, each slice containing voxels and forms a 1:1 mapping of each of the slices, in order, to a corresponding tile in a digital flat volume. The method defines, for at least one voxel in a plurality of voxels in the digital flat volume, a neighborhood that includes the at least one voxel and adjacent voxels that are within the corresponding tile of the voxel, and adjacent voxels to the at least one voxel that are within the preceding tile in the digital flat volume, and adjacent voxels to the voxel that are within the next tile in the digital flat volume. The at least one voxel is rendered according to the adjacent voxels in its defined neighborhood. The volume image having the at least one rendered voxel is displayed.

Abstract: A method for displaying a diagnostic image acquires the diagnostic digital image and applies one or more pattern recognition algorithms to the acquired diagnostic digital image, detecting at least one feature within the acquired diagnostic digital image. At least a portion of the acquired diagnostic digital image displays with a marking at the location of the at least one detected feature. At least one detected feature displays under a first set of image display settings for a first interval, then under at least a second set of image display settings for a second interval.

Abstract: A system is disclosed that is configured for microcalcifications (mcc) detecting by forming a plurality of true mcc clusters and a plurality of normal clusters, gathering spot and cluster features from said clusters, extracting linear structure features, and using said spot, cluster and linear structure features in mcc detector algorithm training.

Abstract: A method for detecting a linear structure in a digital mammographic image, using a processor or computer at least in part, locates at least one microcalcification candidate cluster in the image data and extracts a first region of interest that encloses the at least one microcalcification candidate cluster. The first region of interest is processed to identify feature points that correspond to geometric structures in the first region of interest. A linear detection algorithm is applied by a repeated process that selects a line model from a predefined set of line models and analyzes the line model to determine whether a linear structure is present in the first region of interest.

Abstract: A method is disclosed for verifying linear structures in a digital mammographic image, comprising providing a configurable linear structure verifier in mammography computer assisted diagnosis system; optionally using an microcalcification candidate cluster driven linear structure verification methodology; selecting parameters for the linear structure verifier from a plurality of different parameter generating sources, at least one of which is controllable by human input; configuring the verifier according to selected parameters; and verifying linear structure using cascade rules.

Abstract: A method for detecting tubing in a radiographic image of a patient, executed at least in part by a control logic processor, obtains radiographic image data for a patient and identifies a region of interest in the radiographic image. A gradient magnitude image of the region of interest is formed and analyzed to identify one or more linear features by defining a band lying substantially within the region of interest and having a center point and repeating a sequence with two or more iterations of assigning a rotation angle for the rotatable band about the center point and computing the ensemble average of gradient magnitude values along each of a plurality of lines extending within the rotatable band at the defined rotation angle, then computing relative magnitudes for the lines. The one or more identified linear features are evaluated according to the results of the ensemble average computing.

Abstract: A method of microcalcification detection in a digital mammographic image identifies one or more potential microcalcification sites in the mammographic image according to spot clustering. Each of the one or more potential microcalcification sites is assigned either as a member of a positive candidate set or as a member of a rejected candidate set. Optionally at least one subsequent classifier process that selectively assigns zero or more members of the positive candidate set to the rejected candidate set is executed, according to results from the at least one subsequent classifier process. One or more members of the rejected candidate set are selected as a reclamation candidate set according to results from the initial and any subsequent classifier process. One or more members of the reclamation candidate set are assigned either back to the rejected candidate set or to the positive candidate set according to results from a reclamation classifier process.

Abstract: A method for imaging the surface of a tooth, the method executed at least in part on a computer records a first set of images of the tooth, wherein each image in the first set of images is illuminated according to a pattern oriented in a first direction. A second set of images of the tooth are recorded, wherein each image in the second set of images is illuminated according to a pattern oriented in a second direction that is shifted more than 10 degrees with respect to the first direction. A first contour image is reconstructed according to the recorded first set of images and a second contour image according to the recorded second set of images. A residual image is formed as a combination of the first and second contour images. The residual image is analyzed and surface conditions of the tooth reported.

Abstract: A method of providing a corrected reconstructed computed tomography image accesses image data for computed tomography images of a subject, identifying a subset of the computed tomography images that contain high density features. At least one high density feature is detected in each of the identified subset. The high density feature is classified and a compensation image is formed by distributing pixels representative of tissue over the classified high density feature. A difference sinogram is generated for each image in the identified subset of images by subtracting a first sinogram of the high density feature from a second sinogram of the original image. A resultant sinogram is generated for each image in the identified subset by adding a third sinogram generated according to the compensation image to the difference sinogram. The corrected reconstructed computed tomography image is formed according to the resultant sinogram generated for each image in the identified subset of images.

Abstract: A method for detecting a linear structure in a digital mammographic image, using a processor or computer at least in part, locates at least one microcalcification candidate cluster in the image data and extracts a first region of interest that encloses the at least one microcalcification candidate cluster. The first region of interest is processed to identify feature points that correspond to geometric structures in the first region of interest. A linear detection algorithm is applied by a repeated process that selects a line model from a predefined set of line models and analyzes the line model to determine whether a linear structure is present in the first region of interest.

Abstract: A method for image linear structure detection in medical imaging. The method includes locating microcalcification (mcc) candidate spots in a mammographic image; forming candidate clusters; assigning ranks to the candidate clusters; identifying linear structures in the neighborhood where the candidate clusters reside; and altering the ranks of the candidate clusters for which linear structures have been identified in the neighborhood.

Abstract: An image fusion method which is used for medical applications. The method includes: (a) acquiring a first image with a planned radiation region; (b) acquiring a second image with actual radiation region; (c) determining if user defined landmarks have been placed on the first and second images, if user defined landmarks are present go to step (d), if not go to step (e); (d) pre-transforming the first image or second image or both images; and (e). performing a first delineation step on the actual radiation region. The method further includes: (f) determining if the delineation is correct, if yes go to step (g), if not go to step (h); (g) fusing the first and second image and exit process; and (h) selecting multiple guide points around the actual radiation region in the second image, wherein the guide points are position adaptable points; which are placed near but not on the boundaries of the region; and (i) performing a second delineation step on the actual radiation region and go to step (f).

Abstract: A method for determining a location of an object in a radiographic image by segmentation of a region in the image comprises the steps of: determining a first image intensity that is characteristic of high image intensities in the region; determining a second image intensity that is characteristic of low image intensities outside of the region; and determining if a pixel is added to or removed from the region based on the similarity of the pixel's intensity to the first and second intensity.

Abstract: An image fusion method for medical applications, comprising: a. acquiring a first image with a planned radiation region; b. acquiring a second image with actual radiation region; c. determining if user defined landmarks have been placed on the first and second images, if user defined landmarks are present go to step (d), if not go to step (e); d. pre-transforming the first image or second image or both images; e. performing a first delineation step on the actual radiation region; f. determining if the delineation is correct, if yes go to step (g), if not go to step (h); g. fusing the first and second image and exit process; and h. selecting multiple contour points around the actual radiation region in the second image; i. performing a second delineation step on the actual radiation region and go to step (f).