33 results about "Model based segmentation" patented technology

A method for segmenting intravascular images includes acquiring a series of digitized images acquired from inside a vessel, each said image comprising a plurality of intensities corresponding to a 2-dimensional grid of pixels, providing a precomputed set of shapes for modeling contours of vessel wall boundaries, wherein a contour can be expressed as a sum of a mean shape and a inner product of shape modes and shape weights, initializing a boundary contour for one of said set of images, initializing said shape weights by projecting a contour into said shape modes, updating said shape weights from differential equations of said shape weights, and computing a contour by summing said mean shape and said inner product of shape modes and updated shape weights.

A system and method for detecting the aortic valve is provided. The method comprises: (a) casting rays on a slice of a computed tomography (CT) dataset of an aorta; (b) computing a Gaussian model for voxels on the slice, wherein the Gaussian model produces a threshold; (c) growing a circle from a point within the aorta until control points of the circle reach the threshold; (d) computing a repulsion vector for each control point reaching the threshold; (e) repositioning the circle according to an average of the repulsion vectors, wherein if the circle is within the aorta, repeating steps (c-e) until the circle is not within the aorta; (f) calculating a statistical value for the circle; (g) projecting a copy of the circle onto an adjacent slice; (h) reducing the radius of the copy of the circle; and (i) repeating steps (c-h) on remaining CT slices until the aortic valve is detected.

There is provided a hierarchical shadow detection system for color aerial images. The system performs well with highly complex images as well as images having different brightness and illumination conditions. The system consists of two hierarchical levels of processing. The first level involves, pixel level classification, through modeling the image as a reliable lattice and then maximizing the lattice reliability using the EM algorithm. Next, region level verification, through further exploiting the domain knowledge is performed. Further analyses show that the MRF model based segmentation is a special case of the pixel level classification model. A quantitative comparison of the system and a state-of-the-art shadow detection algorithm clearly indicates that the new system is highly effective in detecting shadow regions in an image under different illumination and brightness conditions.

In a magnetic resonance (MR) apparatus and segmentation method, a region in an MR image, acquired from a scan of a patient with an MR scanner of the apparatus, is provided to a computer for segmentation of the region from the overall image dataset. The segmentation takes place based on a classification of image elements of the image dataset, and the classification is iteratively re-trained in a weakly supervised learning algorithm based on examination-specific information provided to the computer.

In a method and apparatus for automatic or semi-automatic segmentation of a 3D image data set, acquired by a medical imaging apparatus, of an examination region that includes an organ, the 3D image data set is provided to a computer / processor, which is also provided with information with designating the type of organ imaged in the examination region. The 3D image data set is automatically segmented in the computer / processor using a model-based segmentation algorithm, wherein the designated type of organ is used as a basis of the model. The 3D data set is also automatically or semi-automatically segmented using a greyscale value-based segmentation algorithm. At least one of the segmentation results is displayed.

A system (100) and method is provided for performing a model-based segmentation of an anatomical structure in a medical image of a patient. The medical image (022) is accessed. Moreover, model data (162) is provided which defines a deformable model for segmenting the type of anatomical structure. The model-based segmentation of the anatomical structure is performed by adapting the deformable model to the anatomical structure in the medical image using an adaptation technique. In accordance with the present invention, performing the model based segmentation further comprises determining from patient data (042) medical information which is predictive of an appearance of the anatomical structure in the medical image, and adjusting or setting a segmentation parameter based on the medical information so as to adjust the model-based segmentation to said predicted appearance of the anatomical structure in the medical image, the segmentation parameter being a parameter of i) the deformable model or ii) the adaptation technique. Advantageously, the system and method are enabled to better cope with the inter-patient and inter-disease-stage variability in the appearance of anatomical structures.

There is provided a hierarchical shadow detection system for color aerial images. The system performs well with highly complex images as well as images having different brightness and illumination conditions. The system consists of two hierarchical levels of processing. The first level involves, pixel level classification, through modeling the image as a reliable lattice and then maximizing the lattice reliability using the EM algorithm. Next, region level verification, through further exploiting the domain knowledge is performed. Further analyses show that the MRF model based segmentation is a special case of the pixel level classification model. A quantitative comparison of the system and a state-of-the-art shadow detection algorithm clearly indicates that the new system is highly effective in detecting shadow regions in an image under different illumination and brightness conditions.

The present invention relates to a system (100) for segmenting a plurality of objects in image data using simultaneous model-based image segmentation. A surface mesh is adapted to each object to be segmented. To avoid or reduce the possibility of mesh collision,a plurality of connecting edges for connecting two proximal meshes are used. A connection energy defined for the plurality of connecting edges allows controlling the spatial relationship between the first and second mesh. This is achieved by including in the connection energy expression terms that will increase the connection energy when the lengths of edges of the plurality of connecting edges connecting the first and second mesh decrease. Using the reference configuration of the plurality of connecting edges defined based on the pre- positioned first and second mesh allows taking into account prior knowledge about a typical spatial relationship between the first and second object of the plurality of objects.

A system and method is provided which obtains different medical images (210) showing an anatomical structure of a patient and having been acquired by different medical imaging modalities and / or different medical imaging protocols. The system is configured for fitting a first deformable model to the anatomical structure in the first medical image (220A), fitting a second deformable model to the anatomical structure in the second medical image (220B), mutually aligning the first fitted model and the second fitted model (230), and subsequently fusing the first fitted model and the second fitted model to obtain a fused model (240) by augmenting the first fitted model with a part of the second fitted model which is missing in the first fitted model; or adjusting or replacing a part of the first fitted model based on a corresponding part of the second fitted model having obtained a better fit. The fused model represents a multimodal / multi-protocol segmentation of the anatomical structure, and provides a user with a more comprehensive understanding of the anatomical structure than known models.

A system and method is provided for performing a model-based segmentation of a medical image which only partially shows an anatomical structure. In accordance therewith, a model is applied to the image data of the medical image, the model-based segmentation providing an adapted model having a first model part having been adapted to the first part of the anatomical structure in the medical image of the patient, and a second model part representing the second part of the anatomical structure not having been adapted to a corresponding part of the medical image. Metadata is generated which identifies the first model part to enable the first model part to be distinguished from the second model part in a further processing of the adapted model. Advantageously, the metadata can be used to generate an output image which visually indicates to the user which part of the model has been personalized and which part of the model has not been personalized. Other advantageous uses of the metadata in the further processing of the adapted model have also been conceived.

The invention relates to a system (100) for segmenting a plurality of objects in image data using simultaneous model-based image segmentation. A surface mesh is adapted to each object to be segmented. To avoid or reduce the possibility of mesh collision, a plurality of connecting edges for connecting two proximal meshes are used. A connection energy defined for the plurality of connecting edges allows controlling the spatial relationship between the first and second mesh. This is achieved by including in the connection energy expression terms that will increase the connection energy when the lengths of edges of the plurality of connecting edges connecting the first and second mesh decrease. Using the reference configuration of the plurality of connecting edges defined based on the pre-positioned first and second mesh allows taking into account prior knowledge about a typical spatial relationship between the first and second object of the plurality of objects.