Abstract: A method and system that provides users with additional information regarding imagery analyzed by computer-aided detection (CAD) systems is described. A user selects a region of the analyzed imagery. Information is then derived from computational measurements of the region obtained during CAD processing. The region selected by the user does not necessarily have to include a displayed CAD system detection. The information includes a description of the computational measurement and the value of the measurement, both of which are provided in clinically relevant terms.

Abstract: Disclosed are methods, and associated systems comprising processors, input devices and output devices, of detecting regions of interest in a tomographic breast image. The methods may comprise: acquiring tomographic breast image data; deriving a plurality of synthetic sub-volumes from the tomographic breast image data; wherein each subvolume is defined by parallel planar top and bottom surfaces; wherein planar top and bottom surfaces of successive subvolumes are parallel to each other; and wherein a top planar surface of a sub-volume is offset from a top planar surface of a prior sub-volume, such that successive sub-volumes overlap; for each sub-volume, deriving a two-dimensional image; for each two-dimensional image, identifying regions of interest therein; deriving at least one region of interest of potential clinical interest from a plurality of identified regions of interest; and outputting information associated with at least one derived region of interest of potential clinical interest.

Abstract: Methods, a system, and a computer readable medium are presented that detect and classify mass-like regions exhibiting spiculated and/or dense characteristics with high sensitivity and at acceptable false positive rates. One or more suspicious masses are identified in medical imagery of the breast. In accordance with certain embodiments, for each suspicious mass located, a quantitative measure of spiculation and quantitative measure of density are computed. At least one classification scheme is then selected for each suspicious mass according to both quantitative measures. Each classification scheme is developed using true positives and false positives with similar quantitative measures. In accordance with certain other embodiments, for each suspicious mass located, a measure of breast location is computed. At least one classification scheme is then selected for each suspicious mass according to the measure of breast location.

Abstract: A decision rule is used that examines the computer-aided detected (CAD) regions of interest in a computed tomography (CT) slice pair taken from volumetric medical CT scan to determine whether the detected regions of interest are part of the same object is disclosed. Segmentation is performed after initially detecting a region of interest but before calculating features in order to refine the boundaries of the detected regions of interest. Segmentation occurs in the two-dimensional slices by segmenting the region of interest on each slice. Adjacent slices are examined to determine if adjacent objects are actually part of the same structure. If they are not, the objects are split apart. In this way, three-dimensional objects are formed from two-dimensional segmentations.

Abstract: A method and system that provides users with additional information regarding imagery analyzed by computer-aided detection (CAD) systems is described. A user selects a region of the analyzed imagery. Information is then derived from computational measurements of the region obtained during CAD processing. The region selected by the user does not necessarily have to include a displayed CAD system detection. The information includes a description of the computational measurement and the value of the measurement, both of which are provided in clinically relevant terms.

Abstract: A method for refining shape estimates of detected abnormalities in medical images, particularly for the detection of pulmonary lesions in CT imagery is described. A cue point is refined prior to an initially segmentation of the lesion. A radial gradient is computed for points on an initial segmented lesion. Portions of the lesion with radial gradients deviating beyond a threshold angle are removed from the lesion. Registering imagery from more than one CT exam uses a high intensity structure, essentially bone, to provide coarse and fine alignment of a set of two-dimensional images is also described. A MIP image is formed from the three-dimensional images. A second MIP image is then formed from imagery. The second MIP image is correlated with the first MIP image to determine a preferred registration location.

Abstract: A method and system for automated detection and handling of film feeding failures in a high-volume CAD environment. The method provides for batch processing a set of films including multiple film cases including the steps of providing a number count of the number of films corresponding to each film case and identifying a difference between the processed number and the number count as a process error for the film case. The method also provides for batch processing a set of films including multiple film cases including the steps of providing at least one error check on the status of processing the films in the set of films and completing processing of all film cases in the set of films after a process error is identified in one film case.

Abstract: The method and system for exploiting information from multiple images in a mammographic computer-aided detection application is disclosed. A pair of images is obtained by a CAD system. The images are processed to produce a set of regions of interest (ROIs) to be associated with each image. A ROI is selected from the first image of the pair. This ROI is identified and matched to a ROI in the second image. The single image feature values are obtained by the two ROIs of the image pair. Transforming the image feature value to an integer value produces a pair of integers for each image feature value. The pair of integers defines the element of the pre-determined co-occurrence matrix. An element of a predetermined co-occurrence matrix is selected to provide evidence value for the ROI of the first image.

Abstract: A method and system for the use of a CAD algorithm that can be used to automatically detect retained colonic fluid and the rectal tube in computed tomographic (CT) imagery of a patient's colon is disclosed. The CAD algorithm can then electronically subtract the fluid and rectal tube from the images and the modified CT imagery can then be displayed to a user, such as a radiologist. Both the original and modified CT imagery will be stored for future presentation and review. The user, including the radiologist or other medical personnel, will have the option to toggle between displaying and reviewing the modified and original imagery. After subtraction, the radiologist will be able to view the imagery containing all pertinent information regarding the colonic lumen and any suspect region within the colon. Additionally, full processing of the scan is possible even when fluid retention in the colon is greater than fifty percent in any region.

Abstract: The present invention provides for the use of computer-aided detection (CAD) system output displays for providing accurate representations of areas for subsequent exams. Since the CAD output, unlike the original medical imagery, is not used during the initial reading, the radiologist does not mark it until a final determination is reached regarding subsequent procedures. Additionally, since the CAD output contains versions of the original imagery, the regions indicated by the radiologist are shown in the context of the particular anatomical detail for a given patient. This detail assists the technologist, other physicians and patients in more efficiently and accurately locating the exact area for subsequent exams.

Abstract: This invention provides an information fusion method for multiple indicators of cancers detected with multiple channels. Each channel consists of specifically tuned detectors, features, classifiers and Bayes networks. The outputs of the Bayes networks are probabilities of malignancy for the detections passing the corresponding classifier.

Abstract: This invention provides a method for detecting abnormalities in medical images, particularly for the detection of polyps in the colon from computed tomography imagery. Specifically a set of colon masks is input to a detector where summations over spherical volumes with two different radii are computed. Abnormalities are detected based on the ratio of spherical summation values computed for every pixel location.

Abstract: A method for generating billing statements using information relating to patient identification and film images from patients. The method provides a billing output from a CAD system including the steps of performing a processing operation on patient cases with a CAD system and identifying a status associated with the output of the CAD system. The CAD processing status is computed and stored for each case in association with the patient information. A database storing the joint information provides an efficient method for generating billing statements.

Abstract: This invention relates to a method and system for remotely monitoring computer-aided detection (CAD) system processing status. In film-based CAD systems digital images are created by a film digitizer, which is typically loaded with 50 or 100 films. Occasionally, film feeding errors occur which halt the digitization. This invention provides a method and system for detecting the stoppage and for notifying an operator who is not in the vicinity of the digitizer. Notification is accomplished by a variety of methods including pager, telephone, cell phone, and mobile computing devices. In addition to notification of stoppages, the operator may choose to be notified when a certain number of films remain to be processed. This allows the digitizer to be loaded with additional films before the CAD system completes processing of the originally loaded set of films. System efficiency is increased by eliminating idle intervals where the CAD system is stopped awaiting input data.

Abstract: The present invention provides for the use of computer-aided detection (CAD) system output displays for providing accurate representations of areas for subsequent exams. Since the CAD output, unlike the original medical imagery, is not used during the initial reading, the radiologist does not mark it until a final determination is reached regarding subsequent procedures. Additionally, since the CAD output contains versions of the original imagery, the regions indicated by the radiologist are shown in the context of the particular anatomical detail for the given patient. This detail assists the technologist in more efficiently and accurately locating the exact area for subsequent exams.

Abstract: A computer aided detection method and system to assist radiologists in the reading of medical images. The method and system has particular application to the area of mammography including detection of clustered microcalcifications and densities. A microcalcification detector is provided wherein individual detections are rank ordered and classified, and one of the features for classification is derived using a multilayer perceptron. A density detector is provided including an iterative, dynamic region growing module with embedded subsystem for rank ordering and classification of a best subset of candidate masks. A post processing stage is provided where detections are analyzed in the context of a set of images for a patient. Three analysis methods are used to distribute a limited number of detections across the image set and further within each image, and additionally to perform a normalcy classification.

Abstract: A method and system for tracking medical images and associated digital images for diagnostic evaluation. The system includes a scanner for digitizing one or more medical images defining a case to thereby produce one or more digitized medical images and for reading a machine-readable tracking identifier attached to each medical image of the case. A server associates the tracking identifier with one or more digitized medical images and one or more computer-aided diagnostic (CAD) images, wherein the one or more CAD images correspond to the one or more digitized medical images that are processed using a CAD algorithm. The system stores the associated tracking identifier, the one or more digitized medical images, and the one or more CAD images in a storage device. The server receives and processes a medical image request including the tracking identifier to retrieve at least one of the one or more digitized medical images or the one or more CAD images from the storage device using the tracking identifier.