General Electric Company

Srikanth Suryanarayanan

Yogisha Mallya

Rakesh Mullick

Krishna Seetharam Shriram

Ajay Gopinath

Robert F Senzig

James Vradenburg Miller

Vidya Pundalik Kamath

Mukta Chandrashekhar Joshi

Arunabha Shasanka Roy

Mitali Janardan More

Nithin Nagaraj

Xiaoye Wu

David Allen Langan

Sandeep Dutta

Paul Edgar Licato

Rahul Bhotika

Wesley David Turner

Navneeth Subramanian

Umesha Perdoor Srinivas Adiga

Paulo Ricardo (dos Santos) Mendonca

Tara Janen Mahan

A technique is provided for extracting one or more features of interest from one or more projection images. The technique includes accessing projection images comprising at least one feature of interest enhanced by a contrast agent, generating a contrast agent null image based on the projection images, generating a bone mask based on the contrast agent null image, and generating a bone extracted image based on the bone mask.

System and method for extracting features of interest from an image

A system and method includes acquisition of a set of image data comprising a plurality of image voxels and isolation of a set of pulmonary emboli candidates from the plurality of image voxels. The system and method also includes application of a non-linear contrast enhancement to the set of pulmonary emboli candidates, filtration of the enhanced set of pulmonary emboli candidates, output of a final set of pulmonary emboli candidates, and creation of an image comprising the final set of pulmonary emboli candidates.

System and method of pulmonary emboli detection for computed tomography

A technique for automatically labeling a CT image of the brain with anatomical information. The anatomical information is obtained from an atlas of the brain prepared from an MR image of the brain. The atlas contains image data that is referenced to the Talairach coordinate system. The atlas is aligned to the CT image and the coordinate system of the CT image data is transformed to the Talairach coordinate system. The alignment of the CT image and the atlas is performed using anatomical landmarks that are visible on both the CT image and the atlas. The CT image is then labeled automatically with the anatomical information in the atlas.

Brain image alignment method and system

A method includes performing an automatic partitioning of Neuro-vessels into a plurality of anatomically relevant circulatory systems using a CT system.

Vasculature partitioning methods and apparatus

A technique is provided for utilizing a model of an anatomical feature to facilitate the segmentation of the anatomical feature from its background in a medical image. A global alignment of the model with a region in the patient's image data that generally corresponds to the anatomical feature is performed in one embodiment. Internal structural features within the model are then aligned with their corresponding structural features in the patient's image data. The portion of the patient's image data that is aligned with the model of the anatomical feature is then segmented from the remaining portions of the patient's image data that are not aligned with the model.

Method and system for image segmentation using models

A method of identifying one or more occlusions in vasculature located in a region of interest, includes extracting vasculature from the region of interest; identifying a subject geometry of the extracted vasculature; and comparing the subject geometry to a predetermined geometry to identify a blockage. A device for identifying one or more occlusions in vasculature located in a region of interest is also presented.

Device and method for identifying occlusions

A technique for producing a three-dimensional segmented image of blood vessels and automatically labeling the blood vessels. A scanned image of the head is obtained and an algorithm is used to segment the blood vessel image data from the image data of other tissues in the image. An algorithm is used to partition the blood vessel image data into sub-volumes that are then used to designate the root ends and the endpoints of major arteries. An algorithm is used to identify a seed-point voxel in one of the blood vessels within one of the sub-volume of the partition. Other voxels are then coded based on their geodesic distance from the seed-point voxel. An algorithm is used to identify endpoints of the arteries. This algorithm may also be used in the other sub-volumes to locate the starting points and endpoints of other blood vessels. One sub-volume is further sub-divided into left and right, anterior, medial, and posterior zones. Based on their location in one of these zones, the voxels corresponding to the endpoints of the blood vessels are labeled. Starting from these endpoints, the artery segments are tracked back to their starting points using an algorithm that simultaneously labels all of the blood vessel voxels along the path with a corresponding anatomical label identifying the blood vessel to which it belongs.

Vascular image extraction and labeling system and method

A method is provided for identifying a location of a region of interest in a volumetric image scan that includes a plurality of slices of an object and wherein each slice, in turn, includes a plurality of pixels. The method includes setting a predetermined pixel intensity threshold corresponding to a particular region of interest; identifying target pixels for each slice from the plurality of pixels that exceed the predetermined pixel intensity threshold; creating an energy profile from the target pixels for each slice; and comparing the energy profile to a predefined energy profile to determine the location of the region of interest.

Method for registration and navigation of volumetric scans using energy profiles

A technique is provided for modeling a network relationship via providing a graphical representation of the network relationship and labeling the graphical representation based on a symbol sequence. Further, one or more tools is provided by the present technique for interactively visualizing and/or analyzing the graphical representation of the network relationship based on the symbol sequence.

Graph extraction labelling and visualization

A technique is provided for automatically generating a bone mask in CTA angiography. In accordance with the technique, an image data set may be pre-processed to accomplish a variety of function, such as removal of image data associated with the table, partitioning the volume into regionally consistent sub-volumes, computing structures edges based on gradients, and/or calculating seed points for subsequent region growing. The pre-processed data may then be automatically segmented for bone and vascular structure. The automatic vascular segmentation may be accomplished using constrained region growing in which the constraints are dynamically updated based upon local statistics of the image data. The vascular structure may be subtracted from the bone structure to generate a bone mask. The bone mask may in turn be subtracted from the image data set to generate a bone-free CTA volume for reconstruction of volume renderings.

Method and apparatus for segmenting structure in CT angiography

A method for improving a resolution of an image is provided. The method includes reconstructing an image of an initial portion of an object at an initial resolution, and reconstructing an additional portion of the object at an additional resolution.

Systems and methods for improving a resolution of an image

A technique is provided for segmenting a structure of interest from a volume dataset. The technique identifies regions of the structure using templates having characteristics of the structure of interest. The identified regions may then undergo a constrained growth process using dynamic constraints that may vary based on local statistics associated with the identified structure regions. Edges within the volume may be determined using gradient data determined by evaluating the strongest gradient between each pixel and all adjacent pixels. The edge data may be used to prevent the constrained growing process from exceeding the boundaries of the structure of interest.

Method and apparatus for extracting multi-dimensional structures using dynamic constraints

A technique is provided for partitioning an imaged volume into two or more sub-volumes. The technique identifies partition lines which separate the sub-volumes by generating a profile, such as a bone profile, which is then analyzed to determine the placement of the partition lines. In one embodiment, placement of the partition lines is determined automatically by applying one or more sets of hierarchical rules to the profile. After separation of the imaged volume into sub-volumes, each sub-volume may be differentially segmented such that segmentation is customized for the sub-volume. Likewise, after separation of the imaged volume into sub-volumes, the acquisition parameters for each sub-volume may be customized for subsequent acquisitions.

Growing community of inventors

Karnataka, India

Srikanth Suryanarayanan