Siemens Corporate Research, Inc.

Siemens Medical Solutions USA, Inc.

Siemens Corporation Research, Inc.

Shang-Hong Lai

Ming Fang

Benjamin L Odry

Li Zhang

Yuntao Cui

A computer-implemented method for intervertebral disc alignment includes providing a spine image and a click point on the spine image, applying an adaptive thresholding technique to segment vertebrae regions at the click point from the spine image, and filtering segmented vertebrae regions with a morphological operation. The method further includes estimating a multi-scale orientation field from filtered segmented vertebrae regions, extracting an intervertebral disc region by applying region growing for each scale, integrating the multi-scale orientation field in a locally segmented intervertebral disc region based on the intervertebral disc region, estimating a disc centerline from the filtered segmented vertebrae regions, and fusing an integrated multi-scale orientation field with the disc centerline based on associated confidence measures to provide an intervertebral disc alignment.

System and method for detecting intervertebral disc alignment using vertebrae segmentation

A method for matching images includes the step of providing a template image and an input image. A Laplacian-of-Gaussian filtered log (LOG-log) image function is computed with respect to the template image and the input image to obtain a Laplacian-of-Gaussian filtered template image and a Laplacian-of-Gaussian filtered input image, respectively. An energy function is minimized to determine estimated geometric transformation parameters and estimated photometric parameters for the input image with respect to the template image. The energy function is formed by weighting non-linear least squared differences of data constraints corresponding to locations of both the Laplacian-of-Gaussian filtered template image and the Laplacian-of-Gaussian filtered input image. The estimated geometric transformation parameters and the estimated photometric parameters are output for further processing. The method allows for image matching under non-uniform illumination variations.

Method for image alignment under non-uniform illumination variations

A method for matching images is provided that includes the step of providing a template image and an input image. The images include pixels, each pixel having an intensity associated therewith. An energy function formed by weighting a sum of squared differences of data constraints corresponding to locations of both the template image and the input image is minimized to determine estimated geometric and spatially-varying illumination-parameters for the input image with respect to the template image. The estimated geometric and spatially-varying illumination parameters are outputted for further processing.

Method for matching images using spatially-varying illumination change models

A fast localization with advanced search hierarchy system for fast and accurate object localization in a large search space is based on an assumption that surrounding regions of a pattern within a search range are always fixed. The FLASH system comprises a hierarchical nearest-neighbor search system and an optical-flow based energy minimization system. The hierarchical nearest-neighbor search system produces rough estimates of the transformation parameters for the optical-flow based energy minimization system which provides very accurate estimation results and associated confidence measures.

Flash system for fast and accurate pattern localization

A blind image restoration system uses total variational (TV) regularization to allow discontinuities in a true image function. The system first updates image blur parameters to minimize the energy function with the motion parameters and restored image. The motion parameters between subsequent frames in the image sequence are then updated to minimize the energy function with the blur parameters and restored image. The restored image is then updated by using a preconditioned conjugate gradient algorithm to minimize the energy function derived from the TV regularization formulation. The TV-based energy function is then computed by using the currently updated parameter values. If the relative difference between the current energy function value and the energy value computed in the previous iteration is within a threshold, then it is converged and the restored image is outputted. If it has not converged, the signal flows back to update the parameters.

Total variational blind image restoration from image sequences

An illumination compensation system for correcting smooth intensity variations due to illumination changes is based on an assumption that an underlining image reflectance function is approximately a piecewise constant and that an image irradiance function is spatially smooth. The system first takes the logarithm of an image brightness function. Gradient constraints are then computed using a finite difference. Reliable gradient constraints are selected based on a local uniformity test. A process is subsequently applied to estimate the logarithmic irradiance function. A logarithmic irradiance function is subtracted from the logarithmic image brightness function and an exponential operation of the above subtracted image function is taken and an illumination compensated image is outputted from the system.

Illumination compensation system for industrial inspection

A method for localization refinement of inspection patterns comprises the steps of providing a template image comprising pixels in a pattern, each pixel having an intensity, providing an input image having a same pattern of pixels as the template image and calculating an energy function by weighting a sum of modified optical flow constraints at locations of the pixels of both the template image and the input image to determine a shift and rotation between the pattern of the template image and the input image.

Method of localization refinement of pattern images using optical flow constraints

An intensity inhomogeneity correction system includes a log operator which performs a log operation on the intensity values of the original MR image. A regular grid generator partitions the image domain and then a compute and select establishes reliable orientation constraints at grid locations. A bias field surface reconstructor reconstructs a bias field surface from selected orientation constraints with a thin-plate spline by using a preconditioned conjugate gradient. An intensity inhomogeneities remover subtracts an estimated bias function from the original log image and an exponential operation on the bias-field corrected log image provides a corrected image.

Bias field estimation for intensity inhomogeneity correction in MR images

An adaptive hierarchical neural network based system with online adaptation capabilities has been developed to automatically adjust the display window width and center for MR images. Our windowing system possesses the online training capabilities that make the adaptation of the optimal display parameters to personal preference as well as different viewing conditions possible. The online adaptation capabilities are primarily due to the use of the hierarchical neural networks and the development of a new width/center mapping system. The large training image set is hierarchically organized for efficient user interaction and effective re-mapping of the width/center settings in the training data set. The width/center values are modified in the training data through a width/center mapping function, which is estimated from the new width/center values of some representative images adjusted by the user. The width/center mapping process consists of a global spline mapping for the entire training images as well as a first-order polynomial sequence mapping for the image sequences selected in the user's new adjustment procedure.

Neural network based auto-windowing system for MR images

A system for deriving final display parameters for a wide range of MR images consists of a feature generator utilizing both histogram and spatial information computed from an input MR image, a wavelet transform within the feature generator for compressing the size of the feature vector, a competitive layer based neural network for clustering MR images into different subclasses, a bi-modal linear estimation network and a radial bases function network based non-linear estimator for each subclass, as well as a data fusion system using estimates from both estimators to compute the final display parameters.

Robust and automatic adjustment of display window width and center for

Apparatus for detecting activation signals in functional MRI images comprises MRI apparatus for deriving MRI volume data temporal signals for voxels in image slices, the data being grouped in segments respectively corresponding to active and inactive periods. The apparatus includes apparatus for selecting a core region within each segment, where data within a given core region represents a volume data subset of information within a given segment; for performing principal component analysis for each voxel, utilizing a plurality of volume segment data subsets, active and inactive, so as to result in n-dimensional vectors for each volume segment data subset, each vector containing n elements, where n is the dimension of each segment, and in n eigenvectors, one for each vector; for selecting a number of vectors having highest eigenvalues; for obtaining the inner product for each vector for each volume segment data subset and for number of vectors having highest eigenvalues, resulting in coefficients or projections of a number equal to the predetermined number for each volume segment data subset; for performing the foregoing steps for each voxel; for deriving the mean and standard deviations, utilizing the projections; for deriving an energy measure by taking the square root of the sum of the squares of the temporal signals corresponding to respective segments; for calculating a respective activation term for each voxel; and apparatus for displaying an image wherein respective gray scale values corresponding to the activation terms are assigned to activation terms located in respective coordinate positions.

Growing community of inventors

Plainsboro, NJ, United States of America

Shang-Hong Lai