Abstract: A method for volume rendering a volumetric dataset with multiple graphics processing units (GPUs) coupled to a computer system, comprises building a block hierarchical structure of blocks for the volumetric dataset, the block hierarchy comprising a block sequence; partitioning the block sequence into a plurality of groups; determining a target work load for each GPU; allocating each group of the plurality to a respective GPU in accordance with the target load; rendering respective intermediate images by the respective GPUs; and compositing for a final image by blending the respective intermediate images.

Abstract: An image editing system comprises an input device for inputting an image, a graphical user interface for selecting background and object seeds for the image, and an image processor for editing the image. The image processor has various editing routines, including a segmentation routine that builds a graph associated with the image and uses a graph cut algorithm to cut the graph into segments. The user marks certain pixels as “object” or “background” to provide hard constraints for segmentation. Additional soft constraints incorporate both boundary and regional information. Graph cuts are used to find the globally optimal segementation of the image. The obtained solution gives the best balance of boundary and region properties satisfying the constraints.

Abstract: A method for generating classifiers for identifying neuropsychiatric disease includes acquiring functional neuroimaging data. The acquired functional neuroimaging data may be registered to an atlas of the brain. A discriminative mask is generated based on the registered functional neuroimaging data and the generated discriminative mask is applied to the registered functional neuroimaging data. One or more classifiers are generated for identifying neuropsychiatric disease based on the masked functional neuroimaging data. The accuracy of the generated classifiers may be verified. The generated classifiers may then be used to identify neuropsychiatric disease.

Abstract: Machine condition monitoring on a system utilizes a wireless sensor network to gather data from a large number of sensors. The data is processed using a multivariate statistical model to determine whether the system has deviated from a normal condition. The wireless sensor network permits the acquisition of a large number of distributed data points from plural system modalities, which, in turn, yields enhanced prediction accuracy and a reduction in false alarms.

Abstract: A method for directed machine learning includes receiving features including intensity data and location data of an image, condensing the intensity data and the location data into a feature vector, processing the feature vector by a plurality of classifiers, each classifier trained for a respective trained class among a plurality of classes, outputting, from each classifier, a probability of the feature vector belong to the respective trained class, and assigning the feature vector a label according to the probabilities of the classifiers, wherein the assignment produces a segmentation of the image.

Abstract: A system and method for object inspection includes an object modeler; an iterative object segmentor in signal communication with the object modeler for receiving an input image and model parameters and producing a segmented image; a moment transformer in signal communication with the iterative object segmentor for receiving an input image, model parameters and a segmented image and producing estimates of object translation, rotation and scaling; an edge detector and interpolator in signal communication with the moment transformer for receiving an input image, model parameters and estimates and producing a set of line edges; and an iterative optimizer in signal communication with the edge detector and interpolator for receiving an input image, model parameters, estimates and line edges and producing refined estimates of object translation, rotation and scaling.

Abstract: A system and method for modeling a dynamic system using Bayesian filtering, includes a prediction module to predict a state model of the dynamic system, the prediction module generates a prediction density having at least one mode, the state model includes a conditional density function including at least one kernel. Approximating module approximates a measurement probability from a sample set through at least one kernel and an update module updates the conditional density function using the measurement probability and the prediction density. A mode finding and mixture reduction module reduces the number of kernels in the conditional density function.

Abstract: A method for optic disk detection in retinal images, includes: extracting a vessel tree from a retinal image; locating an optic disk in the retinal image using the vessel tree; enhancing a contrast of the optic disk; removing vessels from the contrast enhanced optic disk; detecting a boundary of the optic disk with vessels removed by generating an edge map; projecting the edge map at a plurality of angles by using a radon transform; and estimating a radius and center of the optic disk using the projections.

Abstract: A computer implemented method for creating a depth range buffer for supporting clipping geometries for ray-casting includes inputting image data, establishing a depth range buffer for specifying a start and an end point of each ray, computing a near depth of the image data corresponding to the start point of each ray, computing a far depth of the image data corresponding to the end point of each ray, clipping the volume by restricting ray-casting within the start and end points of the depth range buffer, and rendering a portion of the image data corresponding to the visible depth range.

Abstract: A method of generating a searchable database system for storing and querying Extensible Markup Language (XML) documents is disclosed. A Document Type Description (DTD) associated with one or more XML documents is analyzed to determine a scope of XML documents defined by the DTD. A first set of elements associated with the DTD is identified. The first set of elements is mapped to a relational database. A second set of elements associated with the DTD to be stored in an XML database is identified. A collection of classes is created such that each class defines an object schema. The classes are mapped to a set of corresponding tables, and foreign and primary keys associated with the corresponding tables are identified.

Abstract: A method for selecting the b-values for diffusion weighted magnetic resonance scans. The method includes: identifying a single reference slice within a volume of interest (VOI); progressively changing b-values over a plurality of scans of the reference slice wherein each one of the scans has a different b-value to obtain a plurality of diffusion weighted images; calculating ADC maps for combinations of b-values from the obtained plurality of diffusion weighted images; evaluating the calculated ADC maps; selecting from the evaluation optimal b-values; and using the selected b-values for subsequent scans.

Abstract: A method for reducing B0 inhomogeneous effects in magnetic resonance imaging (MRI). The method includes: obtaining a high-resolution volumetric MR image of the patient, such high-resolution volumetric MR image having B0 inhomogeneous effects; calculating distortion within obtained the high-resolution volumetric MR image of the patient; and correcting the B0 inhomogeneous effects in the obtained high-resolution volumetric image using the calculated distortion.

Abstract: A general purpose method to segment any kind of lesions in 3D images is provided. Based on a click or a stroke inside the lesion from the user, a distribution of intensity level properties is learned. The random walker segmentation method combines multiple 2D segmentation results to produce the final 3D segmentation of the lesion.

Abstract: Apparatus for remotely controlling parameters of an image scanning apparatus includes a software interface for translating commands from an external application for providing scanner control commands to a scanner control machine for control of the parameters; and the software interface includes syntax software for translating the commands from the external application into a given syntax for providing the scanner control commands.

Abstract: A method for monitoring left ventricular (LV) myocardial wall thickness. The method includes: obtaining real time images of a periodically spatially changing myocardium and segmenting the myocardium in such images; calculating wall thickness of the myocardium from each one of the obtained images; and performing a dynamic harmonic analysis of the calculated thickness to determine spatial changes in the thickness of the wall of the myocardium. The method applies the calculated wall thickness to a predictor to determine changes in the thickness of the wall of the myocardium. The method applies the calculated wall thickness to a predictor to determine the periodicity the myocardium.

Abstract: A method for model-based testing of an industrial system includes modeling functionality of an industrial system using a modeling computer language, enhancing the model by adding functionality or refining existing functionality, generating test suites from the system model, and executing the test suites. The modeling computer language is the Unified Modeling Language (UML), wherein modeling includes defining UML use case diagrams to describe relationships among use cases specified for the system and actors who interact with the system according to the use cases, defining UML activity diagrams to model process logic of each use case, wherein the activity diagrams comprise a sequence of activities and transitions, and defining UML class diagrams to specify data categories and attributes that are inputs to the activities of the activity diagrams, wherein data categories relevant for a use case are modeled as test variables in the activity diagram.

Abstract: A fetal parameter or anatomy is measured or detected from three-dimensional ultrasound data. An algorithm is machine-trained to detect fetal anatomy. Any machine training approach may be used. The machine-trained classifier is a joint classifier, such that one anatomy is detected using the ultrasound data and the detected location of another anatomy. The machine-trained classifier uses marginal space such that the location of anatomy is detected sequentially through translation, orientation and scale rather than detecting for all location parameters at once. The machine-trained classifier includes detectors for detecting from the ultrasound data at different resolutions, such as in a pyramid volume.

Abstract: A method and framework are described for detecting changes in a multivariate data stream. A training set is formed by sampling time windows in a data stream containing data reflecting normal conditions. A histogram is created to summarize each window of data, and data within the histograms are clustered to form test distribution representatives to minimize the bulk of training data. Test data is then summarized using histograms representing time windows of data and data within the test histograms are clustered. The test histograms are compared to the training histograms using nearest neighbor techniques on the clustered data. Distances from the test histograms to the test distribution representatives are compared to a threshold to identify anomalies.

Abstract: A method to automatically align magnetic resonance (MR) brain scans for diagnostic scan planning, including: acquiring a three-dimensional (3D) localizer image of a patient; selecting a two-dimensional (2D) coronal view and a 2D transverse view from the localizer image; identifying a mid-sagittal plane (MSP) line in each of the coronal and transverse views and calculating a 3D MSP based on the MSP lines; reconstructing the localizer image based on an equation for the 3D MSP to obtain an image of the MSP of the patient's brain; identifying crista galli (CG) and tip of the occipital bone (TOB) in the image of the MSP of the patient's brain; calculating a transformation matrix based on the MSP, CG and TOB in the image and using the transformation matrix to obtain a scan plan for the patient; and outputting the scan plan for the patient.

Abstract: A computer readable medium embodying instructions executable by a processor to perform a method for hosting components implemented in different computer readable languages within one process. The method includes instantiating a container within a single process, creating a hosting environment for each of a plurality of components, and wherein loading the components by respective environments and wherein the hosting environments are objects instantiated within the container and within the one process, and wherein the plurality of components are implemented in respective a computer readable language, and instantiating a container communication framework object within the container and the one process for processing serialized messages of the components, wherein specific language adapters convert data types of the components to a common implementation, wherein the messages of the plurality of components are processed within the container.