Abstract: Described herein is a framework for multi-view matching of regions of interest in images. According to one aspect, a processor receives first and second digitized images, as well as at least one CAD finding corresponding to a detected region of interest in the first image. The processor determines at least one candidate location in the second image that matches the CAD finding in the first image. The matching is performed based on local appearance features extracted for the CAD finding and the candidate location. In accordance with another aspect, the processor receives digitized training images representative of at least first and second views of one or more regions of interest. Feature selection is performed based on the training images to select a subset of relevant local appearance features to represent instances in the first and second views. A distance metric is then learned based on the subset of local appearance features. The distance metric may be used to perform matching of the regions of interest.

Abstract: A method and system for providing a user interface for polyp annotation, segmentation, and measurement in computer tomography colonography (CTC) volumes is disclosed. The interface receives an initial polyp position in a CTC volume, and automatically segments the polyp based on the initial polyp position. In order to segment the polyp, a polyp tip is detected in the CTC volume using a trained 3D point detector. A local polar coordinate system is then fit to the colon surface in the CTC volume with the origin at the detected polyp tip. Polyp interior voxels and polyp exterior voxels are detected along each axis of the local polar coordinate system using a trained 3D box. A boundary voxel is detected on each axis of the local polar coordinate system based on the detected polyp interior voxels and polyp exterior voxels by boosted 1D curve parsing using a trained classifier. This results in a segmented polyp boundary.

Abstract: A method and system for detecting 3D objects in images is disclosed. In particular, a method and system for Ileo-Cecal Valve detection in 3D computed tomography (CT) images using incremental parameter learning and ICV specific prior learning is disclosed. First, second, and third classifiers are sequentially trained to detect candidates for position, scale, and orientation parameters of a box that bounds an object in 3D image. In the training of each sequential classifier, new training samples are generated by scanning the object's configuration parameters in the current learning projected subspace (position, scale, orientation), based on detected candidates resulting from the previous training step. This allows simultaneous detection and registration of a 3D object with full 9 degrees of freedom. ICV specific prior learning can be used to detect candidate voxels for an orifice of the ICV and to detect initial ICV box candidates using a constrained orientation alignment at each candidate voxel.

Abstract: A method for detecting a substantially cylindrical internal structures and dark structures surrounded by bright intensity values (contrast) in a medical image includes acquiring a medical image. A gradient of the medical image is calculated. Local shape index information for the calculated gradient of the medical image is calculated. Gradient information having a local shape index not indicative of a ridge and rut shapes is removed. Diverging gradient field responses (DGFR) are calculated based on the remaining gradient information. The DGFR responses and relative amount of DGFR responses for the rut and ridge areas is used as a discriminative feature in detecting the substantially cylindrical internal structure as well as darker occluding structures within cylindrical structures such as Pulmonary Emboli.

Abstract: Described herein is a framework for automatically classifying a structure in digital image data are described herein. In one implementation, a first set of features is extracted from digital image data, and used to learn a discriminative model. The discriminative model may be associated with at least one conditional probability of a class label given an image data observation Based on the conditional probability, at least one likelihood measure of the structure co-occurring with another structure in the same sub-volume of the digital image data is determined. A second set of features may then be extracted from the likelihood measure.

Abstract: Automated and semi-automated systems and methods for detection and classification of structures within 3D lung CT images using voxel-level segmentation and subvolume-level classification.

Abstract: Systems and methods for automatic accurate and efficient segmentation and identification of one or more vertebra in digital medical images using a coarse-to-fine segmentation.

Abstract: 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 naïve 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.

Abstract: A system and method of presenting data from a plurality of data sources or objects which simultaneously distributes many sources of such data to many customers. Customer profiles are developed for the recipient describing how important certain characteristics of the data are to each customer. From these profiles, an “agreement matrix” is calculated by comparing the recipient's profiles to the actual profiles of the characteristics of the available data. The agreement matrix thus characterizes the attractiveness of each data to each prospective customer, and is used to produce a series of data which will provide the greatest satisfaction to each customer. The customer's profiles and/or the profiles of the data may be modified to reflect actual usage.

Abstract: A method for computer aided detection of anatomical abnormalities in medical images includes providing a plurality of abnormality candidates and features of said abnormality candidates, and classifying said abnormality candidates as true positives or false positives using a hierarchical cascade of linear classifiers of the form sign(wTx+b), wherein x is a feature vector, w is a weighting vector and b is a model parameter, wherein different weights are used to penalize false negatives and false positives, and wherein more complex features are used for each successive stage of said cascade of classifiers.

Abstract: A method for displaying pre-rendered medical images on a workstation includes receiving three-dimensional medical image data. A region of suspicion is automatically identified within the three-dimensional medical image data. A rendering workstation is used to pre-render the three-dimensional medical image data into a sequence of two-dimensional images in which the identified region of suspicion is featured from a vantage point that is automatically selected to maximize diagnostic value of the two-dimensional images for determining whether the region of suspicion is an actual abnormality. The sequence of pre-rendered two-dimensional images is then stored in a PACS, where it can then be displayed on a viewing workstation.

Abstract: 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.

Abstract: 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 naïve 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.

Abstract: A method and system for providing a user interface for polyp annotation, segmentation, and measurement in computer tomography colonography (CTC) volumes is disclosed. The interface receives an initial polyp position in a CTC volume, and automatically segments the polyp based on the initial polyp position. In order to segment the polyp, a polyp tip is detected in the CTC volume using a trained 3D point detector. A local polar coordinate system is then fit to the colon surface in the CTC volume with the origin at the detected polyp tip. Polyp interior voxels and polyp exterior voxels are detected along each axis of the local polar coordinate system using a trained 3D box. A boundary voxel is detected on each axis of the local polar coordinate system based on the detected polyp interior voxels and polyp exterior voxels by boosted 1D curve parsing using a trained classifier. This results in a segmented polyp boundary.

Abstract: A method and system for polyp segmentation in computed tomography colonogrphy (CTC) volumes is disclosed. The polyp segmentation method utilizes a three-staged probabilistic binary classification approach for automatically segmenting polyp voxels from surrounding tissue in CTC volumes. Based on an input initial polyp position, a polyp tip is detected in a CTC volume using a trained 3D point detector. A local polar coordinate system is then fit to the colon surface in the CTC volume with the origin at the detected polyp tip. Polyp interior voxels and polyp exterior voxels are detected along each axis of the local polar coordinate system using a trained 3D box. A boundary voxel is detected on each axis of the local polar coordinate system based on the detected polyp interior voxels and polyp exterior voxels by boosted 1D curve parsing using a trained classifier. This results in a segmented polyp boundary.

Abstract: A method for detecting spherical and ellipsoidal objects is digitized medical images includes providing a 2-dimensional (2D) slice I(x, y) extracted from a medical image volume of a colon, said image volume comprising a plurality of intensities associated with a 3 grid of points, generating a plurality of templates of different sizes whose shape matches a target structure being sought in said slice, calculating a normalized gradient from said slice, calculating a diverging field gradient response (DFGR) for each of the plurality of masks with the normalized gradient, and selecting a strongest response as being indicative of the position and size of the target structure.

Abstract: A method for performing computer-assisted diagnosis includes receiving a plurality of two-dimensional views of an internal structure, defining a search space around one or more areas of analysis within each view of the internal structure, calculating a convex hull for each area of analysis within each search space of each view of the internal structure, determining a set of foreground pixels that are located within the convex hull for each area of analysis within each search space within each view of the internal structure, and for each area of analysis, merging the set of foreground pixels that are located within the convex hull from each view.

Abstract: Image acquisition refers to the taking of digital images of multiple views of the object of interest. In the processing step, the constituent images collected in the image acquisition step are selected and further processed to form a multimedia sequence which allows for the interactive view of the object. Furthermore, during the Processing phase, the entire multimedia sequence is compressed and digitally signed to authorize it viewing. In the Storage and Caching Step, the resulting multimedia sequence is sent to a storage servers. In the Transmission and viewing step, a Viewer (individual) may request a particular multi-media sequence, for example, by selecting a particular hyperlink within a browser, which initiates the downloading, checking of authorization to view, decompression and interactive rendering of the multi-media sequence on the end-users terminal, which could be any one of a variety of devices, including a desktop PC, or a hand-held device.

Abstract: A method and system for detecting 3D objects in images is disclosed. In particular, a method and system for Ileo-Cecal Valve detection in 3D computed tomography (CT) images using incremental parameter learning and ICV specific prior learning is disclosed. First, second, and third classifiers are sequentially trained to detect candidates for position, scale, and orientation parameters of a box that bounds an object in 3D image. In the training of each sequential classifier, new training samples are generated by scanning the object's configuration parameters in the current learning projected subspace (position, scale, orientation), based on detected candidates resulting from the previous training step. This allows simultaneous detection and registration of a 3D object with full 9 degrees of freedom. ICV specific prior learning can be used to detect candidate voxels for an orifice of the ICV and to detect initial ICV box candidates using a constrained orientation alignment at each candidate voxel.

Abstract: A method for detecting a substantially cylindrical internal structures and dark structures surrounded by bright intensity values (contrast) in a medical image includes acquiring a medical image. A gradient of the medical image is calculated. Local shape index information for the calculated gradient of the medical image is calculated. Gradient information having a local shape index not indicative of a ridge and rut shapes is removed. Diverging gradient field responses (DGFR) are calculated based on the remaining gradient information. The DGFR responses and relative amount of DGFR responses for the rut and ridge areas is used as a discriminative feature in detecting the substantially cylindrical internal structure as well as darker occluding structures within cylindrical structures such as Pulmonary Emboli.