Siemens Medical Solutions USA, Inc.

Siemens Corporation

Siemens Aktiengesellschaft

Siemens Corporate Research, Inc.

Jason Jenn-Kwei Tyan

Tong Fang

Gregory G Slabaugh

Yunqiang Chen

Gozde Unal

Ming Fang

Ti-chiun Chang

Alexander Zouhar

Hongcheng Wang

Fred McBagonluri

Hui Xie

Rupen Melkisetoglu

Lin Cheng

A method and system for structure enhancement and noise reduction of medical images using adaptive filtering is disclosed. The method utilizes feature estimation methods to determine multiple feature values for each pixel in an input image. Each pixel is then filtered using a filter type selected based on the feature values for that pixel.

System and method for structure enhancement and noise reduction in medical images

A method of designing hearing aid molds is disclosed whereby two shapes corresponding to graphical images of ear impressions are registered with each other to facilitate joint processing of the hearing aid design. In a first embodiment, a first graphical representation of a first ear impression is received and a feature, such as the aperture of the ear impression, is identified on that graphical model. A first vector is generated that represents the orientation and shape of that first feature. The three-dimensional translation and rotation of that first vector are determined that are necessary to align the first vector with a second vector representing the orientation and a shape of a feature, once again such as the aperture, of a second ear impression. In another embodiment, this alignment is then refined by minimizing the sum of the distances between points on the first and second graphical representations.

Method and apparatus for the registration of 3D ear impression models

A method of designing hearing aid molds is disclosed whereby skeletons, or simplified models, of two ear impressions are used to register the graphical representations of the molds to facilitate the joint design of hearing aid shells. The center points of at least a portion of contour lines on the surface of each ear impression are identified. Then, for each ear impression, by connecting these center points to each adjacent center point, a skeleton that represents a simplified model of an ear impression is generated. Vectors describing the distance and direction from the points of each skeleton to an anatomical feature of each ear impression are identified to obtain a correspondence between the points of each skeleton. Three-dimensional translations and rotations of a feature vector of at least one of the skeletons are determined to achieve alignment of the skeleton of one ear impression with the skeleton of another impression.

Method and apparatus for the rigid registration of 3D ear impression shapes with skeletons

A method identifying apertures of ear impressions is disclosed. A plurality of contour lines associated with an ear impression are determined and a difference value between a value of a characteristic, such as the diameter, of each contour line and that characteristic of an adjacent contour line is determined. The aperture is identified as being that contour line having the greatest difference value. The contour lines are determined by identifying where a plane intersects the surface of the graphical representations. In another embodiment, the contour lines are assigned a weight. A contour index is then calculated for each contour line as a function of the difference value and these weights. According to this embodiment, the aperture is identified as being a contour line that is adjacent to that contour line having the greatest contour index.

Method and apparatus for aperture detection of 3D hearing aid shells

A system and method for image reconstruction is disclosed. The method divides iterative image reconstruction into two stages, in the image and Radon space, respectively. In the first stage, filtered back projection and adaptive filtering in the image space are combined to generate a refined reconstructed image of a sinogram residue. This reconstructed image represents an update direction in the image space. In the second stage, the update direction is transformed to the Radon space, and a step size is determined to minimize a difference between the sinogram residue and a Radon transform of the refined reconstructed image of the sinogram residue in the Radon space. These stages are repeated iteratively until the solution converges.

System and method for image reconstruction

A method for removing speckle noise from ultrasound images includes providing a plurality of digitized ultrasound (US) images, each image comprising a plurality of intensities corresponding to a domain of points on a 2-dimensional grid, initializing an initial gain associated with each of said plurality of US images, estimating a signal sub-space by averaging over each US image divided by its associated gain, and estimating an updated gain by projecting its associated image into said signal sub-space. If an absolute difference of said updated gain and said initial gain is less than a pre-determined quantity, obtaining an averaged image from said signal sub-space, estimating an optimal Wiener filter from said plurality of US images and said averaged image, and filtering said averaged image with said Wiener filter, wherein said speckle noise is substantially minimized.

System and method for adaptive spatial compounding for ultrasound imaging

A method for registering two three-dimensional shapes is disclosed whereby the two shapes are represented as zero level set of signed distance functions and the energy between these two functions is minimized. In a first embodiment, two undetailed ear impression models are rigidly registered with each other. In another embodiment, a detailed ear impression is initially aligned with an undetailed ear impression model and, then, the detailed ear impression model is rigidly registered with the undetailed ear impression model as a function of the signed distance functions. In accordance with another embodiment, an undetailed ear impression model is non-rigidly registered with a template ear impression model as a function of the signed distance functions.

Method and apparatus for the rigid and non-rigid registration of 3D shapes

A method for multiple image restoration includes receiving a plurality of images corrupted by noise, and initializing a reduced noise estimate of the plurality of images. The method further includes estimating a probability of distributions of noise around each pixel and the probability of the signal, estimating mutual information between noise on the plurality of images based on the probabilities of distributions of noise around each pixel and the joint distribution of noise, and updating each pixel within a search range to determine a restored image by reducing the mutual information between the noise on the plurality of images.

Mutual information regularized Bayesian framework for multiple image restoration

A method for estimating feature values from a digitized image includes calculating a gradient of an image, defining a filter weighting function, convolving the gradient with the filter weighting function, integrating over a subdomain of the convolved gradient to calculate components of a cost matrix &#x3a6;, wherein the cost matrix minimizes a distance metric in a frequency domain of the image, solving for the eigenvalues of the cost matrix, and calculating one or more features from the cost matrix eigenvalues. One or more predesigned bandpass filters can be applied to the image, and cost matrix eigenvalues are analyzed to select one or more appropriate bandpass filters to be applied to the image.

System and method for efficient feature estimation for medical images

A method of designing filters for filtering digitized images includes constructing a set of difference-of-Gaussian (DoG) filters that partition a frequency space, forming a linear combination of said DoG filters to form a trial filter, convolving said trial filter with a training image to obtain a trial image, summing a square difference of said trial image and a target image, wherein if said sum is a minimum, outputting said trial filter as a final filter, and using a singular value decomposition on said final filter wherein an eigenvector corresponding to the largest eigenvalue of the final filter is obtained.

System and method for efficient filter design through weighted difference of Gaussian filters

A gradient-based image enhancement and restoration method and system which applies an orientation-isotropy adaptive filter to the gradients of high structured regions, and directly suppresses the gradients in the noise or texture regions. A new gradient field is obtained from which image reconstruction can progress using least mean squares. The method generally comprises: inputting image data; calculating image gradients; defining the gradients as having large or small coherence; filtering the large coherence gradients for edge enhancement; suppressing the small coherence gradients for noise reduction; assembling an enhanced gradient field from the filtered large coherence and suppressed small coherence gradients; and optimizing the assembled gradient field into a restored image.

Gradient-based image restoration and enhancement

A method and system for improving image quality by compounding a plurality of images to mitigate the effects of image noise. The method utilizes the independency between noise components for multiple image compounding. An effective measurement is designed to regularize the independency between noise in a traditional generative model based filtering framework, thereby enabling a more robust algorithmic solution to inaccurate signal/noise modeling. The method generally comprises selecting a plurality of images, calculating the residual error on each image; calculating the noise likelihood of each image, calculating the signal likelihood of the image, performing an independence analysis to regularize an independence constraint between the residual errors of the images, and summing the signal likelihood, noise likelihood and pairwise independency to approximate the joint independency between the residual errors.

Image compounding based on independent noise constraint

A method for three dimensional image segmentation of a volume of interest includes providing a three dimensional image of the volume of interest, providing an initial polyhedron having a plurality of mesh vertices within the three dimension image and determining an image-based speed at each vertex of the polyhedron using an ordinary differential equation (ODE) that describes the vertex motion of the polyhedron. The method further includes determining a regularization term at each vertex of the polyhedron, updating the plurality of mesh vertices of the polyhedron, integrating the image-based speed of each vertex over a face of the polyhedron, and determining an output polyhedron approximating a shape of the volume of interest.

Active polyhedron for 3D image segmentation

A system and method for synchronously processing ear shells for hearing aids comprising: loading data associated with a first and second ear shell; determining whether to perform a rigid or non-rigid registration of the data associated with the first and second ear shells, wherein the rigid registration is performed when shapes of the first and second ear shells are within a predetermined threshold, and the non-rigid registration is performed when the shapes of the first and second ear shells are not within the predetermined threshold; registering the data associated with the first and second ear shells; processing the first and second ear shells, wherein the processing is synchronously performed; and outputting the processed first and second ear shells to a display device.

Synchronized processing of ear shells for hearing aids

A system and method for modeling binaural shells for hearing aids, wherein the system is configured to load data associated with a first and a second ear shell. The system is further configured to register the data associated with the first and the second ear shells and process the first ear shell and the second ear shells, wherein the processing on the first ear shell is automatically performed on the second ear shell.

Growing community of inventors

Princeton, NJ, United States of America

Jason Jenn-Kwei Tyan