A user had to manually select a cross-sectional image indicating features of a finding and a cross-sectional image displayed in a report, from a three-dimensional medical image. Provided is an image processing apparatus that includes: a unit configured to acquire a target finding of a medical image; a unit configured to calculate an image feature quantity of a type associated in advance with the target finding, for each of a plurality of cross-sectional images of the medical image; and a unit configured to identify a cross-sectional image from the plurality of cross-sectional images based on the calculated image feature quantity. Operation of selecting a cross-sectional image by a doctor can be omitted, and the burden can be reduced.

A method and apparatus for delineating an object within a volumetric medical image. The method comprises obtaining auto-generated contour data for the object within the volumetric medical image, the auto-generated contour data defining a set of auto-generated contours forming a delineation structure for the object, selecting a subset of auto-generated contours for manual editing, and identifying the selected subset of auto-generated contours to a user. In some examples, the method further comprises presenting at least the selected subset of auto-generated contours to the user, receiving user feedback for at least one auto-generated contour, deriving a full set of contours forming a revised delineation structure for the object based at least partly on an interpolation of the auto-generated contour(s) for which user feedback was received, and storing contour data defining the derived full set of contours forming the revised delineation structure for the object within at least one data storage device.

A method and system for acquiring, processing, storing, and displaying x-ray mammograms Mp tomosynthesis images Tr representative of breast slices, and x-ray tomosynthesis projection images Tp taken at different angles to a breast, where the Tr images are reconstructed from Tp images.

An encoder includes a processor and a memory. The memory includes code as instructions that cause the processor to receive geometric data and a viewpoint associated with the geometric data, and quantize the geometric data based on the viewpoint using a plurality of view-dependent quantization values each having a quantized distance based on a proximity to the viewpoint.

A system and method for modifying features in designs of objects to make them physically capable of being manufactured using additive manufacturing techniques and machines is provided.

Methods and systems are described for treatment of atrial fibrillation. Certain embodiments provide methods of assessing a risk of thromboembolic stroke in a patient. The method comprises acquiring image data and determining an indicator of a degree of fibrosis of a patient's left atrium (LA) based on the image data. A treatment modality is then determined and administered to the patient based on the analysis of the image data.

A method for generating an interactive 2D projection of a 3D model includes steps of applying hierarchical defect data to the 3D model of a multi-part object, generating heatmap data based at least in part on the hierarchical defect data, and overlaying the heatmap data on the 3D model. The method also includes steps of extracting data corresponding to the 3D model and including the heatmap data after the overlaying step, and creating the interactive 2D projection based on the extracted data.

A user had to manually select a cross-sectional image indicating features of a finding and a cross-sectional image displayed in a report, from a three-dimensional medical image. Provided is an image processing apparatus that includes: a unit configured to acquire a target finding of a medical image; a unit configured to calculate an image feature quantity of a type associated in advance with the target finding, for each of a plurality of cross-sectional images of the medical image; and a unit configured to identify a cross-sectional image from the plurality of cross-sectional images based on the calculated image feature quantity. Operation of selecting a cross-sectional image by a doctor can be omitted, and the burden can be reduced.

Registration-based interpolation between images slices is provided. In various embodiments, a plurality of 2D images is read. Each of the plurality of 2D images represents a slice of a 3D volume. A plurality of annotations is read for a subset of the plurality of 2D images. The annotations comprise at least one anatomical label. 2D images lacking annotations are selected from the plurality of 2D images. The at least one anatomical label is propagated from the subset of the plurality of 2D images to the selected 2D images by deformable registration.

Methods and software assisting a user in working with images of histological sections to increase the user's productivity and decrease the need for extensive expertise in anatomy. In some embodiments, the methods include methods of assisting a user in creating a 3D volume image of a tissue block from a series of images of histological sections taken from the tissue block. In some embodiments, the methods include methods of automatedly registering a live-view or stored histological section image to a tissue block atlas. In some embodiments, the methods include methods of annotating a histological section image with information from a tissue block atlas based on user input(s) associated with the tissue block atlas. In some embodiments, the methods include methods of automatedly controlling operation of an imaging modality, such as an optical microscope, based on user input(s) associated with a tissue block atlas. These and other methods may be embodied in various configurations of software.