Abstract: In a preferred embodiment a radiologist traces the pulmonary artery and pulmonary veins visible in a set of CT images and identifies the arteries and veins. The radiologist's identification of the pulmonary arteries and pulmonary veins is then received by an image analyzer and combined with the analyzer's identification of the pulmonary arteries to form a combined identification; and the analyzer then reviews this combined identification of the pulmonary arteries to detect any pulmonary embolisms. The radiologist's identification of any pulmonary embolisms is compared with the analyzer's identification of any pulmonary embolisms to determine if there are any embolisms identified by the analyzer that were not identified by the radiologist.

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 navigation tool that provides a side-by-side display of two temporally related medical images of the same region of a patient. A plurality of lines extend between the images, at least a first line beginning at a feature at a first location in a first image and ending at a corresponding feature at a corresponding location in the second image and at least a second line extending from a feature found at a second location in one of the images toward a corresponding second location in the other image and indicating a feature found in one image but not the other. Preferably, the navigational tool also includes a scroll bar alongside the display of medical images. On the scroll bar are a series of markers, each marker corresponding to one of the plurality of lines that extend between the images and preferably being aligned with that line.

Abstract: Detection inputs are classified using two thresholds. In a preferred embodiment, a multiplicity of inputs are scored and the scored inputs are searched to locate an input that has a score greater than a first threshold. If such input is found, every input having a score in excess of a second threshold lower than the first threshold is identified as belonging to a first class of interest. If no input is found having a score in excess of the first threshold, no inputs are identified as belonging to the first class.

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: 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.