Abstract: A region-growing method for identifying nodules in an anatomical volume segments a 3-D image volume by controlled voxel growth from seed points. The process is based on creation and use of a distance map for tracking the distance of vessel voxels from a predetermined location. A volume map is created that identifies the largest sphere that can pass between a voxel and a predetermined location without touching a non-vessel voxel. The ratio between the distance map and the volume map is analyzed to find regions more likely to contain nodules, the features of which can be extracted or otherwise highlighted.

Abstract: A CAD system pre-analyzes a medical image to automatically determine whether contrast agent was introduced into the patient before forming that image. In one embodiment, contrast agent detection is performed by comparing the voxel values in known blood-containing areas to voxel values of known water-containing areas, and if there is a substantial difference above a preferred threshold, then it is determined that this patient was indeed injected with the contrast agent. Upon finding that the patient was indeed injected with contrast agent, the CAD algorithm then automatically performs both a detection algorithm that uses the contrast agent and one that does not and notifies the clinician that both sets of results are available to look at. However, if it is determined that the patient was not injected with contrast agent, the CAD algorithm does not perform the algorithm that uses the contrast agent does not give the user the option to view any results from such algorithm.

Abstract: A method and system of volume segmentation is disclosed. To address throughput speed and accuracy requirements, the segmentation is divided into two stages: presegmentation and detailed segmentation. In presegmentation, a digital image volume is processed to identify anatomical structures from image backgrounds in a gross manner possibly at reduced image resolution. Detailed segmentation then involves refining and segmenting further the fine details within the anatomical structures identified by presegmentation. One result of the overall volume segmentation algorithm is a volume in which segmented regions of interest, such as nodules, are identified.

Abstract: A method, system, and related computer program products are provided for processing a medical image of a body part according to a computer-aided detection (CAD) algorithm, the medical image having an image border, the body part comprising imaged tissue appearing inside the image border and outlying tissue not appearing in the medical image, wherein likely anatomical abnormalities in the outlying tissue near the imaged tissue border are detected by the CAD algorithm. In one example, the detected likely abnormalities in the outlying tissue are located within a first distance from the imaged tissue border, wherein the first distance corresponds to a spatial ambit of a neighborhood-based feature computed by the CAD algorithm.

Abstract: A method and apparatus for providing testing a computer aided diagnosis (CAD)-based system comprising receiving radiological image of a patient acquired using at least one piece of radiological equipment at least partially controlled by a technologist, the patient being controlled by the technologies relative to the radiological equipment in acquiring said radiological image.

Abstract: An algorithm is quickly scans a digital image volume to detect density nodules. A first stage is based on a transform to quickly highlight regions requiring further processing. The first stage operates with somewhat lower sensitivity than is possible with more detailed analyses, but operates to highlight regions for further analysis and processing. The transform dynamically adapts to various nodule sizes through the use of radial zones. A second stage uses a detailed gradient distribution analysis that only operates on voxels that pass a threshold of the first stage.

Abstract: A region-growing method for identifying nodules in an anatomical volume segments a 3-D image volume by controlled voxel growth from seed points. The process is based on creation and use of a distance map for tracking the distance of vessel voxels from a predetermined location. A volume map is created that identifies the largest sphere that can pass between a voxel and a predetermined location without touching a non-vessel voxel. The ratio between the distance map and the volume map is analyzed to find regions more likely to contain nodules, the features of which can be extracted or otherwise highlighted.

Abstract: Facilitating viewer comparison of a plurality of medical images of at least one body part on a softcopy review workstation is described. First and second medical images are displayed such that the second medical image appears as a spatially registered underlay to the first medical image exposed through an aperture therein. The aperture comprises at least one edge that is viewer-manipulable in a back-and-forth manner so that the first and second medical images can be visually compared with minimal eye movement. For a temporal comparison embodiment, the first and second medical images comprise identical views of the same body part acquired at different times. For a cross-modality comparison embodiment, the first and second medical images are acquired substantially concurrently, or at different times, using different medical imaging modalities. For a bilateral comparison embodiment, the first and second images are corresponding views of two laterally corresponding body parts.

Abstract: A method and apparatus for correcting for a distortion in a mammogram. The method comprises classifying pixels as either likely fat or likely not-fat. The method further comprises identifying a candidate distortion and calculating a histogram of the likely fat and the likely not-fat pixels at the candidate distortion. The method further comprises evaluating a quality of the candidate distortion based on features of the histograms of pixel values in the fat and dense tissue classes. The distortion may be a two dimensional tilt of the plates or a three dimensional deformation of the plates as in a bend.

Abstract: Managing a patient worklist in a radiology environment is described, the patient worklist identifying a plurality of medical imaging cases to be reviewed at a radiology review workstation. For each case, a set of CAD-computed metrics is received, the CAD-computed metrics being derived from an operation of a CAD processing algorithm on that case. According to a preferred embodiment, the cases in the patient worklist are sorted according to at least one of the CAD-computed metrics. The reviewing radiologist is provided with greater insight into, and control over, patient workflow at the radiology review workstation. Also described is a graphical user interface for easy user customization of the case sorting criteria. Examples of case sorting criteria include a number of CAD markers per case metric, a maximum suspiciousness metric, and an anatomical complexity metric.

Abstract: A method and apparatus for providing an independent display system for a computer aided detection (CAD) system that analyzes medical images. The independent display system comprises a screen to display a medical image including any marked regions of interest and a plurality of icons to interact with the screen. For one embodiment, the screen is a touch screen, such that the independent display system does not require a keyboard or cursor controller.

Abstract: Display and navigation for multiple computer-aided detection (CAD) detections is described. A medical image is displayed to a viewer, and a request is received to instantiate CAD-assisted viewing. A timewise presentation sequence for the CAD detections is automatically computed according to a predetermined sequencing criterion. For each CAD detection, an expanded presentation window is displayed for its associated location in the medical image, the expanded presentation windows being displayed according to the timewise presentation sequence. Also described is a navigational tool comprising a plot of an operating curve onto which a computed feature associated with the CAD algorithm can be mapped, the operating curve characterizing an application of the CAD algorithm to a reference database of mammographic cases having known diagnoses.

Abstract: A method and system for computer-aided detection of abnormal lesions in digital mammograms is described, wherein digital films are processed using an automated and computerized method of detecting the order and orientation of a set of films. In one embodiment, anatomic features are used to detect the order, orientation and identification of a film series. In another embodiment of the invention, a technologist feeds films into the system in any order and orientation. After processing, the system provides an output on a display device to a radiologist that is in an order and orientation preferred by the radiologist. In yet another embodiment of the invention, films from one case are distinguished from films of another case. In this manner and through the use of a bulk loader, a large number of films can be stacked together and fed into the system at one time.

Abstract: A review workstation for facilitating interpretation of a medical image by a user is described. The review workstation comprises a display device displaying the medical image to the user, and an input device receiving a graphical identification of a region of interest (ROI) in the medical image that is interesting to the user. Responsive to the identification of the ROI, a content-based image comparison is performed between the ROI and a resource database, the resource database comprising a collection of resource images previously analyzed by human interpreters and textual information associated with those previous analyses. The content-based image comparison comprises identifying a subset of the resource images similar to the ROI with respect to a preselected set of computed features. The display device subsequently displays to the user at least one of the identified subset of resource images and its associated textual information simultaneously with the ROI.

Abstract: A computer-aided diagnostic method and system provide image annotation information that can include an assessment of the probability, likelihood or predictive value of detected or identified suspected abnormalities as an additional aid to the radiologist. More specifically, probability values, in numerical form and/or analog form, are added to the locational markers of the detected and suspected abnormalities. The task of a physician using such a system as disclosed is believed to be made easier by displaying markers representing different regions of interest.

Abstract: A method and apparatus for analyzing a medical image obtained from one of a plurality of digital modalities, the method comprising transforming or mapping the initial medical image to create a uniform contrast response and appearance regardless of the original modality of the image.

Abstract: A method and apparatus for analyzing a medical image obtained from one of a plurality of modalities, the method comprising normalizing the medical image to create a uniform display quality regardless of the original modality of the image.

Abstract: A computer-aided diagnostic method and system provide image annotation information that can include an assessment of the probability, likelihood or predictive value of detected or identified suspected abnormalities as an additional aid to the radiologist. More specifically, probability values, in numerical form and/or analog form, are added to the locational markers of the detected and suspected abnormalities. The task of a physician using such a system as disclosed is believed to be made easier by displaying markers representing different regions of interest.

Abstract: An algorithm is quickly scans a digital image volume to detect density nodules. A first stage is based on a transform to quickly highlight regions requiring further processing. The first stage operates with somewhat lower sensitivity than is possible with more detailed analyses, but operates to highlight regions for further analysis and processing. The transform dynamically adapts to various nodule sizes through the use of radial zones. A second stage uses a detailed gradient distribution analysis that only operates on voxels that pass a threshold of the first stage.

Abstract: A method, system, and method of doing business in a standards-based medical imaging environment is described in relation to the communication of computer-aided detection (CAD) results among devices, with one embodiment relating to the DICOM standard. CAD results are fixably integrated into the pixels of a secondary image derived from a source image, and the secondary image is transferred using a DICOM Secondary Capture Image Information Object Instance (SCI-IOI). The DICOM SCI-IOI is transferred to a viewing workstation, whereby a clinician can open, manipulate, and view the secondary image in a side-by-side comparison with the source image or derivative images thereof. Advantageously, CAD results are communicated to the clinician in a DICOM-conforming manner independent of whether the viewing workstation supports standard DICOM accommodations, such as CAD Structured Report Information Object Instances (CAD SR-IOIs), for the type of CAD results that need to be presented.