Abstract: In various embodiments, an optimization engine regenerates items included in an interactive page while the user is interacting with the interactive page. In operation, an optimization engine displays a portion of the interactive page during a viewing session. Subsequently, the optimization engine computes a probability distribution for the viewing session over a set of interests based on model parameters and operations performed by the user during the viewing session. The optimization engine then regenerates items that are included in a second portion of the interactive page based on the probability distribution for the viewing session. The optimization engine displays a least a part of the resulting regenerated interactive page. Advantageously, by regenerating items included in the interactive page based on operations performed by the user during the viewing session, the optimization engine reduces the time required for the user to view an item that piques an interest.

Abstract: A method and system for automatic detection and volumetric quantification of bone lesions in 3D medical images, such as 3D computed tomography (CT) volumes, is disclosed. Regions of interest corresponding to bone regions are detected in a 3D medical image. Bone lesions are detected in the regions of interest using a cascade of trained detectors. The cascade of trained detectors automatically detects lesion centers and then estimates lesion size in all three spatial axes. A hierarchical multi-scale approach is used to detect bone lesions using a cascade of detectors on multiple levels of a resolution pyramid of the 3D medical image.

Abstract: Ribs are automatically ordered and paired. After ordering ribs on each side, magnetic and spring functions are used to solve for rib pairing. The magnetic function is used to constrain possible pairs across sides, and the spring function is used to maintain the order on each side while accounting for missing or fused ribs.

Abstract: A method for automatic femur segmentation and condyle line detection. The method includes: scanning a knee of a patient with medical imaging equipment to obtain 3D imaging data with such equipment; processing the obtained 3D imaging data in a digital processor to determine two lines tangent to the bottom of the knee condyles in an axial and a coronal plane; and automatically scanning the patient in the defined plane. The processing includes: determining an approximate location of the knee; using the determined the location to define a volume of interest; segmenting the femur in the defined volume of interest; and determining a bottom point on the femur portion on a right side and a left side of the segmented femur in an axial and a coronal slice to determine the two lines.

Abstract: A method and system for visualizing the spine in 3D medical images is disclosed. A spinal cord centerline is automatically determined in a 3D medical image volume, such as a CT volume. A reformatted image volume is then generated based on the spinal cord centerline. The reformatted image volume can be a straightened spine volume or a Multi-planar Reconstruction (MPR) based volume that follows the natural curve of the spine. The reconstructed volume can be displayed as 2D slices or 3D volume renderings.

Abstract: A method for segmenting image data within a data processing system includes acquiring an image. One or more seed points are established within the image. An advection vector field is computed based on image influences and user input. A dye concentration is determined at each of a plurality of portions of the image that results from a diffusion of dye within the computed advection field. The image is segmented into one or more regions based on the determined dye concentration for the corresponding dye.

Abstract: A method for processing image data for segmentation includes receiving image data. One or more seed points are identified within the image data. Intensity and texture features are computer based on the received image data and the seed points. The image data is represented as a graph wherein each pixel of the image data is represented as a node and edges connect nodes representative of proximate pixels of the image data and establishing edge weights for the edges of the graph using a classifier that takes as input, one or more of the computed image features. Graph-based segmentation such as segmentation using the random walker approach may then be performed based on the graph representing the image data.

Abstract: A method for recovering a contour using combinatorial optimization includes receiving an input image, initializing functions for gradient f, smooth background g, and contour r, determining an optimum of the gradient f of a region R in the input image, extending the optimum of the gradient f of region R to a complement of R, determining an optimum of the smooth background function g for a region Q corresponding to the complement of R, extending the optimum of the smooth background function g of region Q to a complement of Q, and determining an optimum contour r according to the optimum of the gradient f and the optimum of the smooth background function g.

Abstract: A method and system for automatic detection and volumetric quantification of bone lesions in 3D medical images, such as 3D computed tomography (CT) volumes, is disclosed. Regions of interest corresponding to bone regions are detected in a 3D medical image. Bone lesions are detected in the regions of interest using a cascade of trained detectors. The cascade of trained detectors automatically detects lesion centers and then estimates lesion size in all three spatial axes. A hierarchical multi-scale approach is used to detect bone lesions using a cascade of detectors on multiple levels of a resolution pyramid of the 3D medical image.

Abstract: Ribs are automatically ordered and paired. After ordering ribs on each side, magnetic and spring functions are used to solve for rib pairing. The magnetic function is used to constrain possible pairs across sides, and the spring function is used to maintain the order on each side while accounting for missing or fused ribs.

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: Feature processing is provided for lung nodules in computer-assisted diagnosis. A feature that may better distinguish nodules from background is extracted using a Hough transform. Rather than relying on a specific boundary shape, the Hough transform accumulates evidence associated with a region, such as a ring region. The accumulated evidence provides a feature score without requiring a nodule to fit a specific shape. In another approach, a background level is determined from extracted features. Rather than attempting to normalize an image prior to extraction, the features are normalized. The feature normalization and generalized Hough transform extraction may be used together or alone.

Abstract: A method for automatic femur segmentation and condyle line detection. The method includes: scanning a knee of a patient with medical imaging equipment to obtain 3D imaging data with such equipment; processing the obtained 3D imaging data in a digital processor to determine two lines tangent to the bottom of the knee condyles in an axial and a coronal plane; and automatically scanning the patient in the defined plane. The processing includes: determining an approximate location of the knee; using the determined the location to define a volume of interest; segmenting the femur in the defined volume of interest; and determining a bottom point on the femur portion on a right side and a left side of the segmented femur in an axial and a coronal slice to determine the two lines.

Abstract: A method for segmenting image data within a data processing system includes acquiring an image. One or more seed points are established within the image. An advection vector field is computed based on image influences and user input. A dye concentration is determined at each of a plurality of portions of the image that results from a diffusion of dye within the computed advection field. The image is segmented into one or more regions based on the determined dye concentration for the corresponding dye.

Abstract: A method for recovering a contour using combinatorial optimization includes receiving an input image, initializing functions for gradient f, smooth background g, and contour r, determining an optimum of the gradient f of a region R in the input image, extending the optimum of the gradient f of region R to a complement of R, determining an optimum of the smooth background function g for a region Q corresponding to the complement of R, extending the optimum of the smooth background function g of region Q to a complement of Q, and determining an optimum contour r according to the optimum of the gradient f and the optimum of the smooth background function g.

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: Feature processing is provided for lung nodules in computer-assisted diagnosis. A feature that may better distinguish nodules from background is extracted using a Hough transform. Rather than relying on a specific boundary shape, the Hough transform accumulates evidence associated with a region, such as a ring region. The accumulated evidence provides a feature score without requiring a nodule to fit a specific shape. In another approach, a background level is determined from extracted features. Rather than attempting to normalize an image prior to extraction, the features are normalized. The feature normalization and generalized Hough transform extraction may be used together or alone.

Abstract: A method and system for visualizing the spine in 3D medical images is disclosed. A spinal cord centerline is automatically determined in a 3D medical image volume, such as a CT volume. A reformatted image volume is then generated based on the spinal cord centerline. The reformatted image volume can be a straightened spine volume or a Multi-planar Reconstruction (MPR) based volume that follows the natural curve of the spine. The reconstructed volume can be displayed as 2D slices or 3D volume renderings.