摘要:
Systems and methods for generating images for identifying diseases are provided. In one embodiment, a method comprises receiving a first digital radiography (DR) image of at least a portion of a body of a patient, receiving a second DR image of the at least a portion of a body of a patient, the first DR image being captured at a different energy level than the second DR image, and determining common control point locations for both the first and second DR images. The method further comprises generating an optimized DR image by moving portions of a selected one of the first and second DR images with its associated control points to locations that correspond to similar portions of the other of the first and second DR images, applying deformable transformation to one of the first and second DR images and performing a log subtraction on the first and second DR image to generate a dual-energy digital radiography (DEDR) image.
摘要:
Systems, methods and computer-readable storage mediums relate to processing to segment ultrasound images of an object. The processing may be based on three different planes. The processing may include applying a wavelet transform to image data in each plane to extract the texture features; and applying a trained support vector machine to classify the texture features.
摘要:
Systems, methods and computer-readable storage mediums relate to segmenting MR images using multiscale bilateral filtering. Before the multiscale bilateral filtering, the MR images are transformed from the Image Domain to the Radon Domain.
摘要:
Systems, methods, and computer-readable storage media relate to segmenting an image series of at least one image of a region of interest of a subject. The methods, systems, and computer readable storage media can automatically segment interior and exterior boundaries relative to the region of interest (e.g., epicardial and endocardial boundaries with respect to a right ventricle) from an image series by combining sparse matrix transform, a training model, and a localized region based level set function.
摘要:
Systems, methods, and computer-readable storage media relate to providing image guidance that can improve the accuracy of interventional procedures, such biopsy sampling, for example, by accurately providing location information to guide the biopsy needle image. The systems, methods, and computer-readable storage media include generating a 3D multi-modality image that includes a pre-procedure reference image and an ultrasound image; and displaying at least one view, one of the views including a display in-real-time of a position of the interventional device on the multi-modality image with respect to the target site during the procedure.
摘要:
A method is provided that comprises receiving a first digital radiography (DR) image of at least a portion of a body of a patient, receiving a second DR image of the at least a portion of a body of a patient, the first DR image being captured at a different energy level than the second DR image, and determining common control point locations for both the first and second DR images. The method further comprises generating an optimized DR image by moving portions of a selected one of the first and second DR images with its associated control points to locations that correspond to similar portions of the other of the first and second DR images, applying deformable transformation to one of the first and second DR images and performing a log subtraction on the first and second DR image to generate a dual-energy digital radiography (DEDR) image.
摘要:
Systems, methods and computer-readable storage mediums relate to segmenting MR images using multiscale bilateral filtering. Before the multiscale bilateral filtering, the MR images are transformed from the Image Domain to the Radon Domain.
摘要:
Systems and methods for generating images for identifying diseases are provided. In one embodiment, a method comprises receiving a first digital radiography (DR) image of at least a portion of a body of a patient, receiving a second DR image of the at least a portion of a body of a patient, the first DR image being captured at a different energy level than the second DR image, and determining common control point locations for both the first and second DR images. The method further comprises generating an optimized DR image by moving portions of a selected one of the first and second DR images with its associated control points to locations that correspond to similar portions of the other of the first and second DR images, applying deformable transformation to one of the first and second DR images and performing a log subtraction on the first and second DR image to generate a dual-energy digital radiography (DEDR) image.
摘要:
A method is provided that comprises receiving a first digital radiography (DR) image of at least a portion of a body of a patient, receiving a second DR image of the at least a portion of a body of a patient, the first DR image being captured at a different energy level than the second DR image, and determining common control point locations for both the first and second DR images. The method further comprises generating an optimized DR image by moving portions of a selected one of the first and second DR images with its associated control points to locations that correspond to similar portions of the other of the first and second DR images, applying deformable transformation to one of the first and second DR images and performing a log subtraction on the first and second DR image to generate a dual-energy digital radiography (DEDR) image.