Abstract: A method for detecting lymph nodes in a medical image includes receiving image data. One or more regions of interest are detected from within the received image data. One or more lymph node candidates are identified using a set of predefined parameters that is particular to the detected region of interest where each lymph node candidate is located. The identifying unit may identify the one or more lymph node candidates by performing DGFR processing. The method may also include receiving user-provided adjustments to the predefined parameters that are particular to the detected regions of interest and identifying the lymph node candidates based on the adjusted parameters. The lymph node candidates identified based on the adjusted parameters may be displayed along with the image data in real-time as the adjustments are provided.

Abstract: A method for registering a medical image includes acquiring a first medical image of a subject. One or more simulated medical images are synthesized based on the acquired first medical image. One or more matching functions are trained using the first medical image and the simulated medical images. A second medical image of the subject is acquired. The first medical image and the second medical image are registered using the one or more trained matching functions.

Abstract: A method for lesion detection includes acquiring pre-therapy medical image data from a first modality. Post-therapy medical image data is acquired from a second modality. A transformation matrix for transforming from an image space of the first modality to an image space of the second modality is calculated. A volume of interest is defined from the medical image data of the first modality. The volume of interest includes one or more lesions. The volume of interest is automatically copied to the medical image data of the second modality using the calculated transformation matrix. Treatment is directed to the lesion using the medical image data of the second modality including the copied volume of interest data.

Abstract: A method for segmenting a digitized image includes providing a digitized volumetric image comprising a plurality of intensities corresponding to a domain of points in an N-dimensional space, identifying a target structure in said image, forming a window about said target structure whose size is a function of the target scale, and performing a joint space-intensity-likelihood ratio test at each point within said window to determine whether each said point is within said target structure.

Abstract: 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.

Abstract: A system for computer aided detection and decision support includes an ontology of image representations for injecting meaning into and adding relationships among image contents, an image understanding and parsing module in communication with the ontology of image representations for extracting structures from an image including the image contents, and a reasoning engine based in communication with the ontology and the image understanding and parsing module for classifying the image contents, wherein the system receives the image and corresponding descriptive information.

Abstract: 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.

Abstract: A system for knowledge-based image computer aided detection includes a text interpretation system receiving an electronic patient record and outputting an assertion relevant for the electronic patient record, an annotation/detection system detects anatomical and functional structures in input images and interacts with the text interpretation system to receive the assertion and outputting annotated images based on the input images, and an imaging decision support system taking the annotated images and outputting classifications of annotated structures in the annotated images.

Abstract: A system and method for prioritized transmission of scalable compressed data are provided, the system including a database server for receiving an interactive prioritization request from a client and prioritizing transmission of the compressed data relative to a bin optimization in response to the interactive prioritization request; and the method including receiving an interactive prioritization request from a client, prioritizing transmission of the compressed data relative to the bin optimization in response to the interactive prioritization request and transmitting the prioritized compressed data to the client.

Abstract: A framework is disclosed for robust click-point linking, defined as estimating a single point-wise correspondence between a pair of data domains given a user-specified point in one domain. It can also be interpreted as robust and efficient interactive localized registration of a monomodal data pair. To link visually dissimilar local regions, the concept of Geometric Configuration Context (GCC) is introduced. GCC represents the spatial likelihood of the point corresponding to the click-point in the other domain. A set of scale-invariant saliency features are pre-computed for both data, and GCC is modeled by a Gaussian mixture whose component mean and width are determined as a function of the neighboring saliency features and their correspondences. This allows correspondence of dissimilar parts using only geometrical relations without comparing the local appearances. GCC models are derived for three transformation classes: 1) pure translation, 2) scaling and translation, and 3) similarity transformation.

Abstract: Various attributes for medical CAD analysis used alone or in combination are disclosed, including: (1) using medical sensor data and context information associated with the configuration of the medical system to provide recommendations for further acts to be performed for more accurate or different diagnosis, (2) recommending further acts to be performed and providing an indication of the importance of the further act for further diagnosis, (3) distributing the computer-assisted diagnosis software and/or database over multiple systems, and (4) transmitting patient data to a remote system for CAD diagnosis and using the results of the CAD diagnosis at the remote facility.

Abstract: A method of automatic change quantification for medical decision support includes: automatically detecting a structure in a set of medical images; characterizing the detected structure including modeling of deformation characteristics of the detected structure; matching images based on the characterization of the detected structure, wherein a size measure of the detected structure is constrained according to the deformation characteristics; and quantifying a change in the detected structure.

Abstract: A system for providing automatic diagnosis and decision support includes: a medical image database; generative learning and modeling modules that build distributional appearance models and spatial relational models of organs or structures using images from the medical image database; a statistical whole-body atlas that includes one or more distributional appearance models and spatial relational models of organs or structure, in one or more whole-body imaging modalities, built by the generative learning and modeling modules; and discriminative learning and modeling modules that build two-class or multi-class classifiers for performing at least one of organ, structure or disease detection or segmentation.

Abstract: 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.

Abstract: A computer system for automatic selection of a computer-aided detection (CAD) algorithm including a database storing image data, a browser for navigating the data and selecting image data, an application receiving image data selected by the browser, and a selector selecting a CAD algorithm for processing the image data according to at least one of fixed attributes of the image data and an indication of a subject of the image data.

Abstract: A system and method for data compression and visualization includes a system having a compression unit for compressing an input image of voxels in accordance with a weighted visualization importance, and a visualization unit in signal communication with the compression unit for visualizing the voxels in an order corresponding to the weighted visualization importance; and a corresponding method for defining a weighting function responsive to a visualization importance parameter for voxels, deriving an order of transmission for the voxels in correspondence with the weighting function, compressing the voxels with a look-up table indicative of the order of transmission, transmitting the compressed voxels in order of decreasing weighted visualization importance, and where the method is optionally for receiving the compressed voxels in order of decreasing weighted visualization importance, decompressing the voxels with the look-up table indicative of the order of transmission, and visualizing a voxel in the order i

Abstract: By testing for nodule segmentation errors based on the scan data, juxtapleural cases are identified. Once identified, the scan data or subsequent estimation may be altered to account for adjacent rib, tissue, vessel or other structure effecting segmentation. One alteration is to shape a filter as a function of the scan data. For example, an originally estimated ellipsoid for the nodule segmentation defines the filter. The filter is used to identify the undesired information, and masking removes the undesired information for subsequent estimation of the nodule segmentation. Another possible alteration biases the subsequent estimation away from the incorrect information, such as the rib, tissue or vessel information influencing the original estimation. For example, a negative prior or probability is assigned to data corresponding to the originally estimated segmentation for the subsequent estimation.

Abstract: A system and method are provided for prior-constrained mean shift analysis of a data array, the system including a processor, an input adapter in signal communication with the processor for receiving at least one data array, and a prior constraints unit in signal communication with the processor for performing a prior-constrained mean shift analysis on the at least one data array; and the method including receiving initialization data, selecting an initial point relative to the initialization data, Gaussian fitting with a prior-constrained mean shift responsive to the initial point to parse a structure, and setting the parsed structure as a prior constraint.

Abstract: A method for removing a virtual object from a digitized image comprises the steps of computing a point spread function of the intensities of an image, wherein a point spread function is a measure of the blurriness of said image, marking a plurality of points that represent an object of interest in the image, and subtracting the point spread function value from the intensity for each marked point, wherein the object of interest is removed from said image.

Abstract: A system and method for assigning feature sensitivity values to a set of potential measurements to be taken during a medical procedure of a patient in order to provide a medical diagnosis is disclosed. Data is received from a sensor that represents a particular medical measurement. The received data and context data are analyzed with respect to one or more sets of training models. Feature sensitivity values are derived for the particular medical measurement and other potential measurements to be taken based the analysis, and the feature sensitivity values are outputted.