Siemens Medical Solutions Usa, Inc.

Anna Jerebko

Xiang Sean Zhou

Arun Krishnan

Luca Bogoni

Marcos Salganicoff

Matthias Wolf

Sarang Lakare

Toshiro Kubota

Senthil Periaswamy

Maneesh Dewan

Xiaolei Sharon Huang

Harald Steck

Rachid Fahmi

Vaclav Potesil

Jiamin Liu

Haiying Guan

Yangming Ou

A method for segmenting vertebrae in digitized images includes providing a plurality of digitized whole-body images, detecting and segmenting a spinal cord using 3D polynomial spinal model in each of the plurality of images, finding a height of each vertebrae in each image from intensity projections along the spinal cord, and building a parametric model of a vertebrae from the plurality of images. The method further includes providing a new digitized whole-body image including a spinal cord, fitting an ellipse to each vertebrae of the spinal cord to find the major and minor axes, and applying constraints to the major and minor axes in the new image based on the parametric model to segment the vertebrae.

System and method for segmenting vertebrae in digitized images

A method for differentiating pulmonary nodules in digitized medical images includes identifying an object of interest from a digital image of the lungs, computing a first distance map of each point of the object of interest, determining a seed point from the first distance map, starting from the seed point, growing a first region by adding successive adjacent layers of points until a background point is reached, and partitioning the first region into a nodule region and a non-nodule region.

System and method for robust segmentation of pulmonary nodules of various densities

A method for segmenting organs in digitized medical images includes providing a set of segmented training images of an organ, computing a surface mesh having a plurality of mesh cells that approximates a border of the organ, extracting positive examples of all mesh cells and negative examples in the neighborhood of each mesh cell which do not belong to the organ surface, training from the positive examples and negative examples a plurality of classifiers for outputting a probability of a point being a center of a particular mesh cell, computing an active shape model using a subset of center points in the mesh cells, generating a new shape by iteratively deforming the active shape model to fit a test image, and using the classifiers to calculate a probability of each center point of the new shape being a center of a mesh cell which the classifier was trained to recognize.

System and method for organ segmentation using surface patch classification in 2D and 3D images

A method for detecting bone and bone disease using MRI images includes: detecting and segmenting bone borders using dark bone border intensity information from an MRI image; and detecting bone disease within a segmented image region.

Automatic bone detection in MRI images

A method for segmenting tubular structures in medical images includes providing at least a start point and an end point in a digital image volume, minimizing an action surface U(p) which, at each image point p, corresponds to a minimal energy integrated along a path that starts at start point pand ends at p, sliding back on the minimal action surface from an end point to the start point to find a minimal path connecting the terminal points, initializing a level set function with points on the minimal path, and evolving the level set function to find a surface of a structure about the minimal path, wherein the level set function is constrained to be close to a signed distance function and wherein the level set function is prevented from growing wider than a predetermined diameter R, wherein the surface about the minimal path defines a tubular structure.

System and method for robust segmentation of tubular structures in 2D and 3D images

According to an aspect of the invention, a method for training a classifier for classifying candidate regions in computer aided diagnosis of digital medical images includes providing a training set of annotated images, each image including one or more candidate regions that have been identified as suspicious, deriving a set of descriptive feature vectors, where each candidate region is associated with a feature vector. A subset of the features are conditionally dependent, and the remaining features are conditionally independent. The conditionally independent features are used to train a na&#xef;ve Bayes classifier that classifies the candidate regions as lesion or non-lesion. A joint probability distribution that models the conditionally dependent features, and a prior-odds probability ratio of a candidate region being associated with a lesion are determined from the training images. A new classifier is formed from the na&#xef;ve Bayes classifier, the joint probability distribution, and the prior-odds probability ratio.

System and method for lesion detection using locally adjustable priors

A method for segmenting digitized images includes providing a training set comprising a plurality of digitized whole-body images, providing labels on anatomical landmarks in each image of said training set, aligning each said training set image, generating positive and negative training examples for each landmark by cropping the aligned training volumes into one or more cropping windows of different spatial scales, and using said positive and negative examples to train a detector for each landmark at one or more spatial scales ranging from a coarse resolution to a fine resolution, wherein the spatial relationship between a cropping windows of a coarse resolution detector and a fine resolution detector is recorded.

System and method for whole body landmark detection, segmentation and change quantification in digital images

A method of detecting breast masses and calcifications in digitized images, includes providing a plurality of 2-dimensional (2D) digital X-ray projectional breast images acquired from different viewing angles, extracting candidate lesions and 2D features from said 2D projectional images, computing spicularity characteristics of said candidate lesions, including location, periodicity, and amplitude, applying learning algorithms to said candidate lesions to predict a probability of malignancy of said lesion, receiving from said learning algorithm a probability map of detections for each breast image, said detections comprising associating pixels with a probability of being associated with a malignancy, creating a synthetic 2D slice for each X-ray image wherein malignant regions are indicated by ellipses on a non-malignant background, and constructing a synthetic 3-dimensional (3D) image volume from said 2D synthetic slices.

System and method for detection of breast masses and calcifications using the tomosynthesis projection and reconstructed images

A method of extracting a spinal cord from a digitized medical image includes providing a digitized medical image, selecting a set of points from said image as candidates for belonging to the spine, initializing a probability for each candidate point to belong to said spine, minimizing a weighted sum of square differences of image intensities of said candidate points and intensities determined by a mathematical model of said spine to estimate parameter values for said model, calculating a residual error for each point from the differences at each point between an estimated image intensity calculated from said estimated model parameters and an actual image intensity, updating the candidate point probabilities from said residual errors, and eliminating candidate points whose probability falls below a predetermined value.

System and method for automatic extraction of spinal cord from 3D volumetric images

A system and method for segmentation of structures in an image based on curvature slope are provided, the system including a processor, a curvature slope unit in signal communication with the processor for computing curvature slopes in the image and discarding voxels having a slope not satisfying specifications, and a segmentation unit in signal communication with the processor for locating connected clusters of retained voxels; and the method including computing curvature slopes in the image, discarding voxels having a slope not satisfying specifications, and locating connected clusters of retained voxels.

Segmentation of structures based on curvature slope

A system and method for segmenting a structure of interest are provided. The method comprises: segmenting a surface of the structure of interest; and interpolating a border of the structure of interest, wherein the border separates the structure of interest from other structures having similar properties.

System and method for segmenting a structure of interest using an interpolation of a separating surface in an area of attachment to a structure having similar properties

A method of detecting lesions and polyps in a digital image, wherein said image comprises a plurality of 3D volume points, is provided. The method includes identifying a surface in the image, and for each point in the image, calculating a first curvature measure, forming a set of rings of points about each point, each ring being of equal geodesic distance from a center point for the ring, calculating, for each ring, a standard deviation of the first curvature measure, and selecting those rings with a minimum standard deviation for the first curvature measure. A first curvature slope is calculated for the selected rings, those points where the curvature slope departs from the pattern expected for a polyp or lesion are deleted from the surface.

Method of analysis of local patterns of curvature distributions

Systems and methods are provided for automatic 3D segmentation of abnormal anatomical structures such as colonic polyps, aneurisms or lung nodules, etc., in 3D medical imaging applications. For example, systems and methods for 3D lesion segmentation implement a centroid-based coordinate transformation (e.g., spherical transformation, ellipsoidal transformation, etc.) to transform a 3D surface of the lesion from an original volume space into, e.g., a spherical or ellipsoidal coordinate space, followed by interpolation of the transformed lesion surface to enable accurate determination of a boundary between a lesion and surrounding normal structures.

Growing community of inventors

West Chester, PA, United States of America

Anna Jerebko