Abstract: A method (100) of aneurysm analysis (110) and virtual stent simulation (120) for endovascular treatment of sidewall intracranial aneurysms.

Abstract: A method for segmenting mesh models in digital images includes providing (11) a mesh surface model (V, F, E) of a shape embedded in a 3-dimensional space, providing (12) a ground truth segmentation of the mesh surface model, constructing (13) a feature vector vi composed of underlying geometric properties of the mesh at each vertex point, using (14) the ground truth segmentation and the feature vectors to determine weights wij for edges eij where the weights wij are the probabilities of a random walker crossing edges eij between vertices vi and vj in a random walker segmentation initialized with at least two seeds of different labels.

Abstract: The design process for the surgical plan in orthopedics and/or the design of a personalized cutting guide and/or implant are automated in a workflow frame work. Abstracted rules are scripted through a sequence of operations to alter a bone surface or model for fitting an implant. Using bone information for a specific patient, the proper implant and series of cuts are determined using the rules. A corresponding cutting guide may be fitted to the bone information for the specific patient. Surgical planning of bone replacement implants is performed automatically.

Abstract: A method for segmenting mesh models in digital images includes providing (11) a mesh surface model (V, F, E) of a shape embedded in a 3-dimensional space, providing (12) a ground truth segmentation of the mesh surface model, constructing (13) a feature vector vi composed of underlying geometric properties of the mesh at each vertex point, using (14) the ground truth segmentation and the feature vectors to determine weights wij for edges eij where the weights wij are the probabilities of a random walker crossing edges eij between vertices vi and vj in a random walker segmentation initialized with at least two seeds of different labels.

Abstract: An automated method for aneurysm analysis including: extracting shape descriptors from test vessel data; generating an aneurysm probability map for the test vessel data using the shape descriptors; detecting the presence of the aneurysm on the test vessel data; localizing the aneurysm in the probability map; and separating the aneurysm from the probability map.

Abstract: Active lighting is provided for stereo reconstruction (30) of edges (11) of a Delta-8 bundle. Stereo images of a device with edges (11) are captured (24). The image capture (24) is repeated under different lighting conditions, such as illuminating (22) the edges (11) from different directions. The images from each viewing or capture direction are combined (28). The combined images are used to stereographically reconstruct (30) the edges (11).

Abstract: An automated method for aneurysm analysis including: extracting shape descriptors from test vessel data; generating an aneurysm probability map for the test vessel data using the shape descriptors; detecting the presence of the aneurysm on the test vessel data; localizing the aneurysm in the probability map; and separating the aneurysm from the probability map.

Abstract: A method for determining geometric properties of a target shape such as a shape of a perimeter of a strut shield (36) for use in a gas turbine (10). The method includes obtaining a digital image of at least a portion of a first object including a first feature (164) (106). The image including the first feature (164) is displayed on a display device (108). During a reconstruction process, one or more control points (168A, 168B, 168C, 168D) are associated with feature points (164A, 164B, 164C) along an extent of the displayed first feature (164) (109). Using the associated one or more control points (168A, 168B, 168C and 168D), a data file is created that corresponds to the first feature (164) (114). The data file includes geometric properties of the feature points (164A, 164B, 164C).

Abstract: A method for segmenting intracranial aneurysms in digital medical images includes extracting a mesh representing a vessel surface from a volumetric digital image, the mesh comprising a set of points {pi} and edges {eij} respective points, and finding a set of binary labelings that minimizes an energy functional of the labelings and of shape descriptors of each point in the mesh, where the binary labelings segments an aneurysm from the surface by associating one of two labels with each point pi, where a label indicates whether an associated point is on a vessel or on an aneurysm, where the energy functional includes a unary potential term summed over all points that represent a posterior distribution of the labels over the points, and a pairwise potential term summed over all edges that represents neighborhood labeling relationships.

Abstract: The design process for the surgical plan in orthopedics and/or the design of a personalized cutting guide and/or implant are automated in a workflow frame work. Abstracted rules are scripted through a sequence of operations to alter a bone surface or model for fitting an implant. Using bone information for a specific patient, the proper implant and series of cuts are determined using the rules. A corresponding cutting guide may be fitted to the bone information for the specific patient. Surgical planning of bone replacement implants is performed automatically.

Abstract: Active lighting is provided for stereo reconstruction (30) of edges (11) of a Delta-8 bundle. Stereo images of a device with edges (11) are captured (24). The image capture (24) is repeated under different lighting conditions, such as illuminating (22) the edges (11) from different directions. The images from each viewing or capture direction are combined (28). The combined images are used to stereographically reconstruct (30) the edges (11).

Abstract: A method for specifying design rules for a manufacturing process includes providing a training set of 3D point meshes that represent an anatomical structure, for each 3D point mesh, finding groupings of points that define clusters for each shape class of the anatomical structure, calculating a prototype for each shape class cluster, and associating one or more manufacturing design rules with each shape class prototype. The method includes providing a new 3D point mesh that represents an anatomical structure, calculating a correspondence function that maps the new 3D point mesh to a candidate shape class prototype by minimizing a cost function, calculating a transformation that aligns points in the new 3D point mesh with points in the candidate shape class prototype, and using the rules associated with the shape class prototype, if the candidate shape class prototype is successfully aligned with the new 3D point mesh.

Abstract: A method for determining geometric properties of a target shape such as a shape of a perimeter of a strut shield (36) for use in a gas turbine (10). The method includes obtaining a digital image of at least a portion of a first object including a first feature (164) (106). The image including the first feature (164) is displayed on a display device (108). During a reconstruction process, one or more control points (168A, 168B, 168C, 168D) are associated with feature points (164A, 164B, 164C) along an extent of the displayed first feature (164) (109). Using the associated one or more control points (168A, 168B, 168C and 168D), a data file is created that corresponds to the first feature (164) (114). The data file includes geometric properties of the feature points (164A, 164B, 164C).

Abstract: A method for segmenting intracranial aneurysms in digital medical images includes extracting a mesh representing a vessel surface from a volumetric digital image, the mesh comprising a set of points {pi} and edges {eij} respective points, and finding a set of binary labelings that minimizes an energy functional of the labelings and of shape descriptors of each point in the mesh, where the binary labelings segments an aneurysm from the surface by associating one of two labels with each point pi, where a label indicates whether an associated point is on a vessel or on an aneurysm, where the energy functional includes a unary potential term summed over all points that represent a posterior distribution of the labels over the points, and a pairwise potential term summed over all edges that represents neighborhood labeling relationships.

Abstract: A method (100) of aneurysm analysis (110) and virtual stent simulation (120) for endovascular treatment of sidewall intracranial aneurysms.

Abstract: A method for detecting anatomical features in 3D ear impressions includes receiving a 3D digital image of a 3D ear impression, obtaining a surface of the ear impression from the 3D image, analyzing the surface with one or more feature detectors, the detectors adapted to detecting generic features, including peak features, concavity features, elbow features, ridge features, and bump features, and derived features that depend on generic features or other derived features, and forming a canonical ear signature from results of the detectors, where the canonical ear signature characterizes the 3D ear impression.

Abstract: A method for specifying design rules for a manufacturing process includes providing a training set of 3D point meshes that represent an anatomical structure, for each 3D point mesh, finding groupings of points that define clusters for each shape class of the anatomical structure, calculating a prototype for each shape class cluster, and associating one or more manufacturing design rules with each shape class prototype. The method includes providing a new 3D point mesh that represents an anatomical structure, calculating a correspondence function that maps the new 3D point mesh to a candidate shape class prototype by minimizing a cost function, calculating a transformation that aligns points in the new 3D point mesh with points in the candidate shape class prototype, and using the rules associated with the shape class prototype, if the candidate shape class prototype is successfully aligned with the new 3D point mesh.

Abstract: A method for detecting anatomical features in 3D ear impressions includes receiving a 3D digital image of a 3D ear impression, obtaining a surface of the ear impression from the 3D image, analyzing the surface with one or more feature detectors, the detectors adapted to detecting generic features, including peak features, concavity features, elbow features, ridge features, and bump features, and derived features that depend on generic features or other derived features, and forming a canonical ear signature from results of the detectors, where the canonical ear signature characterizes the 3D ear impression.