Abstract: A method for estimating a region associated with a deformity on a surface portion of the skin of a mammal, the method comprising capturing a three-dimensional image of the surface portion to produce first data, the first data comprising depth data, and generating second data from the first data. The second data comprises curvature data. The method further comprises combining the first data and the second data to produce third data, and performing region growing on the third data.

Abstract: This invention concerns an efficient algorithm for automatic and accurate segmentation of Abdominal Aortic Aneurysm (AAA). The algorithm first identifies the location of the lumen (the inner portion of aorta) and then segments it. The abdominal portion of the lumen is then found using anatomical and geometrical features. This portion of the lumen is straightened using geometrical transformation based on the smoothed centreline. The transformed lumen is then passed through a number of filters, based on geometrical, intensity, gradient and texture features, to search for the existence of the aneurysm. If aneurysm is detected, a deformable model is first initialized to the approximate borders of the aneurysm which are then refined using global and location information.

Abstract: A method of detecting a junction between a lesion and a wall in a CT scan image may include determining the boundary (B) of the wall to an internal space (L), identifying critical points (c1, c2) along the boundary, and selecting one critical point at either side of the lesion as a junction point between the wall and the lesion. The critical points may be points of maximum local curvature and/or points of transition between straight and curved sections of the boundary. The critical points may be selected by receiving first and second seed points (p1, p2) at either side of the lesion, moving the seed points to the boundary if they are not already located on the boundary, and finding the closest critical points to the seed points. The seed points may be determined by displacing the determined junction points (j1, j2) from an adjacent slice of the image into the current slice.

Abstract: A method of detecting the extent of a lung nodule in a scan image comprises fine segmenting (14) a region around the nodule into foreground and background, filling holes within foreground areas (16), region growing the foreground (18) to identify an initial region of interest, determining a mask (20) by enlarging the initial region to contain background and to exclude other foreground regions, determining a spatial map (26) of connectivity within the mask to a point within the initial region, region growing (28) within the mask and determining the maximum edge contrast (30) during region growing. The region of maximum edge contrast identifies the extent of the nodule (32). The position of the nodule may a seed point identified by the user (12). Most preferably, an optimum seed point is determined by iterative determination of seed points (22, 24) so that the determined extent of the nodule is substantially independent of the precise location of the seed point identified by the user.

Abstract: A method of detecting a nodule in a three-dimensional scan image comprises calculating a three-dimensional sphericity index for each point in the scan image (310-330), applying a high sphericity threshold to the sphericity index (340) to obtain a candidate nodule region, and then performing region-growing (350) from the candidate region using a relaxed sphericity threshold to determine an extended region including less spherical parts connected to the candidate region. Optionally, spherical filtering may be applied to the image by matching the spherical filter to the extended region.

Abstract: A method of detecting a nodule in a three-dimensional scan image comprises calculating a three-dimensional sphericity index for each point in the scan image (310-330), applying a high sphericity threshold to the sphericity index (340) to obtain a candidate nodule region, and then performing region-growing (350) from the candidate region using a relaxed sphericity threshold to determine an extended region including less spherical parts connected to the candidate region. Optionally, spherical filtering may be applied to the image by matching the spherical filter to the extended region.

Abstract: An enhanced image is based on an original image. For instance, the original image can be processed using a filter to provide the enhanced image. The original and enhanced images can be displayed side by side or alternately to facilitate a comparison of the original and enhanced images. A user can change one or more enhancement parameters associated with the enhanced image. For example, the user can change the one or more enhancement parameters while viewing the original and enhanced images to determine an effect the change has on the enhanced image. The user can compare the effect of the changed enhancement parameters with his or her own analysis of the original image. The changed enhancement parameters may be applied to other parts of the original image so as to provide a more accurate analysis of those parts.

Abstract: A medical image is analyzed using an algorithm requiring input parameters. Values of the input parameters are derived from metadata, indicating properties of the medical image. For example, the metadata may indicate the type of image acquisition device or settings used to create the medical image. In another example, the metadata may relate to the patient upon whom the image is based. This allows optimum values to be selected for the parameters.

Abstract: An enhanced image is based on an original image. For instance, the original image can be processed using a filter to provide the enhanced image. The original and enhanced images can be displayed side by side or alternately to facilitate a comparison of the original and enhanced images. A user can change one or more enhancement parameters associated with the enhanced image. For example, the user can change the one or more enhancement parameters while viewing the original and enhanced images to determine an effect the change has on the enhanced image. The user can compare the effect of the changed enhancement parameters with his or her own analysis of the original image. The changed enhancement parameters may be applied to other parts of the original image so as to provide a more accurate analysis of those parts.

Abstract: A medical image is analyzed using an algorithm requiring input parameters. Values of the input parameters are derived from metadata, indicating properties of the medical image. For example, the metadata may indicate the type of image acquisition device or settings used to create the medical image. In another example, the metadata may relate to the patient upon whom the image is based. This allows optimum values to be selected for the parameters.

Abstract: A medical image is analyzed using an algorithm requiring input parameters. Values of the input parameters are derived from metadata, indicating properties of the medical image. For example, the metadata may indicate the type of image acquisition device or settings used to create the medical image. In another example, the metadata may relate to the patient upon whom the image is based. This allows optimum values to be selected for the parameters.

Abstract: An enhanced image is based on an original image. For instance, the original image can be processed using a filter to provide the enhanced image. The original and enhanced images can be displayed side by side or alternately to facilitate a comparison of the original and enhanced images. A user can change one or more enhancement parameters associated with the enhanced image. For example, the user can change the one or more enhancement parameters while viewing the original and enhanced images to determine an effect the change has on the enhanced image. The user can compare the effect of the changed enhancement parameters with his or her own analysis of the original image. The changed enhancement parameters may be applied to other parts of the original image so as to provide a more accurate analysis of those parts.

Abstract: An enhanced image is based on an original image. For instance, the original image can be processed using a filter to provide the enhanced image. The original and enhanced images can be displayed side by side or alternately to facilitate a comparison of the original and enhanced images. A user can change one or more enhancement parameters associated with the enhanced image. For example, the user can change the one or more enhancement parameters while viewing the original and enhanced images to determine an effect the change has on the enhanced image. The user can compare the effect of the changed enhancement parameters with his or her own analysis of the original image. The changed enhancement parameters may be applied to other parts of the original image so as to provide a more accurate analysis of those parts.

Abstract: Coronary artery calcification is quantified based on a computed tomography (CT) scan image. A calcified region is identified. The partial calcium content of each pixel in the calcified region can be estimated. For example, expectation maximization of a statistical model of the calcified and background material can be used to estimate the partial calcium content of the pixels. The estimated partial calcium content can be used to generate a map of the partial calcium content in the calcified region. The mass of calcium in the calcified region can be determined based on the map. According to an embodiment, techniques of quantifying calcification that are disclosed herein provide lower inter-scan variation than conventional techniques.

Abstract: A method of detecting a junction between a lesion and a wall in a CT scan image may include determining the boundary (B) of the wall to an internal space (L), identifying critical points (c1, c2) along the boundary, and selecting one critical point at either side of the lesion as a junction point between the wall and the lesion. The critical points may be points of maximum local curvature and/or points of transition between straight and curved sections of the boundary. The critical points may be selected by receiving first and second seed points (p1, p2) at either side of the lesion, moving the seed points to the boundary if they are not already located on the boundary, and finding the closest critical points to the seed points. The seed points may be determined by displacing the determined junction points (j1, j2) from an adjacent slice of the image into the current slice.

Abstract: A method of detecting the extent of a lung nodule in a scan image comprises fine segmenting (14) a region around the nodule into foreground and background, filling holes within foreground areas (16), region growing the foreground (18) to identify an initial region of interest, determining a mask (20) by enlarging the initial region to contain background and to exclude other foreground regions, determining a spatial map (26) of connectivity within the mask to a point within the initial region, region growing (28) within the mask and determining the maximum edge contrast (30) during region growing. The region of maximum edge contrast identifies the extent of the nodule (32). The position of the nodule may a seed point identified by the user (12). Most preferably, an optimum seed point is determined by iterative determination of seed points (22, 24) so that the determined extent of the nodule is substantially independent of the precise location of the seed point identified by the user.

Abstract: A method of detecting a nodule in a three-dimensional scan image comprises calculating a three-dimensional sphericity index for each point in the scan image (310-330), applying a high sphericity threshold to the sphericity index (340) to obtain a candidate nodule region, and then performing region-growing (350) from the candidate region using a relaxed sphericity threshold to determine an extended region including less spherical parts connected to the candidate region. Optionally, spherical filtering may be applied to the image by matching the spherical filter to the extended region.