Abstract: An imaging device and a method for generating a motion-compensated image or video are provided. The imaging device has a data acquisition facility for acquiring image data of a target object. The imaging device is configured to acquire, using a registration facility, a posture of an inertial measurement unit and, on the basis thereof, to carry out a registration between coordinate systems of the inertial measurement unit and the image data. The imaging device is further configured to acquire motion data from the inertial measurement unit arranged on the target object and, by processing the motion data, to generate the motion-compensated image or video.

Abstract: According to embodiments of the present disclosure, methods of and computer program products for operating a plurality of classifiers are provided. A plurality of input entities are read, each input entity having an associated target label. The input entities are provided to a first classifier, and a category of each input entity is obtained therefrom. A feature map is determined for each input entity. Each feature map is provided to each of a set of classifiers, and an assigned label is obtained for each feature map from each of the set of classifiers. Each classifier is associated with one of the categories. For each classifier, the assigned label for each feature map is compared to the target labels to determine a plurality of gradients. The plurality of gradients are masked according to each category, yielding a masked set of gradients for each category. Each classifier is trained according its associated masked gradients.

Abstract: The present invention relates to the field of medical technology, and more particularly, to a digital image classification method for cervical fluid-based cells based on a deep learning detection model. The method comprises the following steps: selecting and labeling positions and categories of abnormal cells or biological pathogens in a digital image of cervical liquid-based smears; performing data normalization processing on the digital image of the cervical liquid-based smears; performing model training to obtain a trained Faster-RCNN model by taking the normalized digital image of the cervical liquid-based smears as an input, and the labeled position and category of each abnormal cell or biological pathogen as an output; and inputting an image to be recognized into the trained model and outputting a classification result.

Abstract: An electronic device is provided comprising: a user interface component configured to output stimuli and receive inputs; a connection component configured to transmit communications to other devices, one or more processors coupled to the user interface component and the connection component; and a computer-readable storage medium containing instructions, that, when executed by the one or more processors, cause the one or more processors to perform actions including: securely storing, at the electronic device, payment information associated with a payment account; detecting a proximate POS terminal; in response to detecting the proximate POS terminal, determining that a mechanical input authorizing a payment transaction has not been locally received at the electronic device within a time period; in response to the determination, presenting a stimulus indicating that the mechanical input has not been locally received; detecting, subsequent to the stimulus presentation, via the user interface component, a mechan

Abstract: A medical image processing apparatus according to an embodiment includes processing circuitry. The processing circuitry acquires image data including image data of a blood vessel of a subject. The processing circuitry performs analysis related to the blood vessel by using the image data, and specifies a region of interest in the blood vessel based on a result of the analysis. The processing circuitry performs fluid analysis on a region other than the region of interest at a first accuracy, and performs fluid analysis on the region of interest at a second accuracy that is higher than the first accuracy.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing cell images using neural networks. One of the methods includes obtaining data comprising an input image of one or more biological cells illuminated with an optical microscopy technique; processing the data using a stained cell neural network; and processing the one or more stained cell images using a cell characteristic neural network, wherein the cell characteristic neural network has been configured through training to receive the one or more stained cell images and to process the one or more stained cell images to generate a cell characteristic output that characterizes features of the biological cells that are stained in the one or more stained cell images.

Abstract: The present disclosure provides an optical tracking system for tracking a location and a posture of a marker. The marker is attachable to a target and configured so that a pattern surface formed inside the marker is visible through an optical system formed in an aperture. The system includes a processor configured to determine the posture of the marker based on a first image in which a part of the pattern surface viewed through the aperture is captured at an infinite focal length, and to determine the location of the marker based on a second image and a third image in which outgoing lights emitted through the aperture in different directions are captured at a focal length shorter than the infinite focal length.

Abstract: An electronic device is provided comprising: a user interface component configured to output stimuli and receive inputs; a connection component configured to transmit communications to other devices, one or more processors coupled to the user interface component and the connection component; and a computer-readable storage medium containing instructions, that, when executed by the one or more processors, cause the one or more processors to perform actions including: securely storing, at the electronic device, payment information associated with a payment account; detecting a proximate POS terminal; in response to detecting the proximate POS terminal, determining that a mechanical input authorizing a payment transaction has not been locally received at the electronic device within a time period; in response to the determination, presenting a stimulus indicating that the mechanical input has not been locally received; detecting, subsequent to the stimulus presentation, via the user interface component, a mechan

Abstract: The disclosure features methods and systems that include illuminating a candidate structure with radiation linearly polarized along a first polarization direction and obtaining a first image of the dendritic structure, illuminating the candidate structure with radiation linearly polarized along a second polarization direction and obtaining a second image of the dendritic structure, where an angle between the first and second polarization directions is at least 10, for a set of pixels corresponding to a first region of the candidate structure in the first and second images, determining a first change in average pixel intensity between the first and second images, and authenticating the candidate structure as a dendritic structure based on the first change in average pixel intensity.

Abstract: A landmark estimating method estimates a position of a landmark that is a hole existing in an object and is a site through which an insertion portion penetrates, in an endoscope image obtained by picking up an image of the object by an endoscope with the insertion portion bent. The landmark estimating method includes estimating an axis of the insertion portion, estimating a boundary of the insertion portion and the object, and estimating the position of the landmark based on the axis and the boundary that are estimated.

Abstract: An example system includes a processor to receive a three-dimensional (3D) volume. The processor can partition the 3D volume into slices. The processor can generate, via a two-dimensional (2D) neural network, slice features based on the slices. The processor can generate, via a three-dimensional (3D) neural network, a three-dimensional (3D) feature volume based on the slice features. The processor can generate, via a volume predictor, a volume prediction based on the 3D feature volume.

Abstract: Methods, apparatuses, systems, and programs are disclosed herein for automatically demarcating segments of an anatomical structure and include providing a processor having a memory, receiving and storing three-dimensional (3D) model data of an anatomical structure of a patient in the memory, generating positional information to orient 3D model data of the anatomical structure, identifying at least one segment of the 3D model data of the anatomical structure based on the positional information, demarcating the at least one identified segment of the 3D model data of the anatomical structure with an identification enhancer that visually distinguishes the at least one identified segment, and providing, for display, the 3D model data of the anatomical structure with the at least one demarcated segment.

Abstract: A method for real-time crowd management includes receiving LiDAR point cloud data from area of interest, forming a 3D static surface model of area of interest from LiDAR point cloud data, obtaining real-time CCTV camera images of area of interest, adding real-time CCTV camera images to 3D static surface model to generate real-time dynamic 3D model, identifying dynamic objects in the 3D model, generating a density map of an area of interest, adding density map to the 3D model, identifying which dynamic objects are people, replacing each person with animated character, displaying real-time dynamic 3D model, monitoring the 3D model in the area of interest for dangerous situations, simulating evacuation of area of interest by manipulating animated characters onto pathways leading away from area of interest, forming an evacuation strategy for crowd, and transmitting a notice of the dangerous situation and the evacuation strategy to an emergency authority.

Abstract: There is provided a method and apparatus for tracking eyes of a user. The method and apparatus may acquire an image of the user, acquire an illuminance of a viewpoint from which the image is captured, and output coordinates of the eyes tracked from the image by operating at least one of a high illuminance eye tracker that operates at a high illuminance or a low illuminance eye tracker that operates at a low illuminance based on the acquired illuminance.

Abstract: A medical image processing apparatus of an embodiment includes a processing circuitry. The processing circuitry extracts a plurality of valve leaflets of a heart valve from image data of a subject. The processing circuitry measures, with respect to at least one valve leaflet of the valve leaflets, a length of a region at which the valve leaflet is in contact with another valve leaflet, in a predetermined reference direction. The processing circuitry controls a display to display a distribution of the length at each of a plurality of positions on the valve leaflet.

Abstract: Disclosed are processes including receiving at least a first and a second image data record corresponding to a first and a second point in time and including a first and a second one or more images of a wound; obtaining an image of the wound from a particular point of view corresponding to the first point in time by analyzing the first image data record; generating a simulated image of the wound from the particular point of view corresponding to the second point in time by analyzing the second image data record; and generating a visual time series view of the wound including at least the image of the wound from the particular point of view corresponding to the first point in time and the simulated image of the wound from the particular point of view corresponding to the second point in time.

Abstract: The invention provides for a medical imaging system (100, 300) comprising a processor (106) for controlling the medical imaging system. Execution of machine executable instructions (112) causes the processor to receive (200) a static angiographic image (114) of a region of interest (322), receive (202) a time series of angiographic images (116, 116?) of the region of interest, construct (204) an image mask (118) using the static angiographic image, determine (206) a time dependent signal (120) for each voxel within the image mask using the time series of angiographic images, construct (208) a composite angiographic image by: assigning (210) a fill time (126) to each voxel within the image mask using an extremum (124) of the time dependent signal if the extremum deviates from an average of the time dependent signal more than a predetermined threshold, and identifying (212) voxels within the image mask as being unfilled voxels.

Abstract: A system and method for assessing an intravenous catheter site is described in embodiments herein. An application accessible on a mobile device may be used to take calibrated photographs of an intravenous catheter site. The resulting calibrated image may be compared to previously taken calibrated images to determine a complication. Success of treatments to the complication may be tracked and the patient's electronic medical record may be updated.

Abstract: The present invention provides a function capable of detecting, with a higher degree of precision, a region that has a high probability of not having been recognized. An image processing apparatus according to the present invention is provided with: a recognition means for recognizing a product from a captured image obtained by capturing an image of a displayed product; and a detection means for detecting a region of a product that is included in the captured image but is not recognized by the recognition means, on the basis of furniture information related to furniture in which the product is displayed.

Abstract: Described here are systems and methods for generating and analyzing co-expression signature data from scalar or multi-dimensional data fields contained in or otherwise derived from imaging data acquired with a medical imaging system. A similarity metric, such as an angular similarity metric, is computed between the data field components contained in pairs of voxels in the data field data. The data fields can be scalar fields, vector fields, tensor fields, or other higher-dimensional data fields. A probability distribution of these similarity metrics can be generated and used as co-expression signature data that indicate pairwise disparities in the data field data.