Abstract: A method and system for automatic bone segmentation and landmark detection for joint replacement surgery is disclosed. A 3D medical image of at least a target joint region of a patient is received. A plurality bone structures are automatically segmented in the target joint region of the 3D medical image and a plurality of landmarks associated with a joint replacement surgery are automatically detected in the target joint region of the 3D medical image. The boundaries of segmented bone structures can then be interactively refined based on user inputs.

Abstract: The disclosed technology automatically (e.g., programmatically) initializes predictive information for tracking a complex control object (e.g., hand, hand and tool combination, robot end effector) based upon information about characteristics of the object determined from sets of collected observed information. Automated initialization techniques obviate the need for special and often bizarre start-up rituals (place your hands on the screen at the places indicated during a full moon, and so forth) required by conventional techniques. In implementations, systems can refine initial predictive information to reflect an observed condition based on comparison of the observed with an analysis of sets of collected observed information.

Abstract: Methods for detecting and analyzing individual nanoparticles of the same, similar, or different sizes co-existing in a fluid sample using multi-spectral analysis are disclosed. A plurality of light sources may be configured to produce a plurality of light beams at different spectral wavebands. An optical assembly may be configured to combine the plurality of light beams into one or more incident light sheets. Each incident light sheet may illuminate one or more nanoparticles in a liquid sample. One or more image detectors may be configured to detect, using a plurality of wavelengths, light scattered or emitted by one or more nanoparticles. The plurality of wavelengths may correspond to the different spectral wavebands of the plurality of light beams. Related apparatus, systems, techniques, and articles are also described.

Abstract: A method, non-transitory computer readable medium, and an image analysis computing device that retrieves, based on a captured version of an object in a received image, training images which display related versions of the object and items of data related to the related versions of the object of the training images. Keypoints which are invariant to changes in scale and rotation in the captured version of the object in the received image and in the related versions of the object in the training images are determined. Changes to the object in the received image based on any of the determined keypoints in the related version of the object which do not match the determined keypoints in the captured version of the object are identified. The identified changes in the captured version of the object in the received image are provided.

Abstract: A position detection device obtains image coordinate groups representing a coordinate of a target object in each acquired image having first and second acquired image groups. The first acquired image group has acquired images obtained at an image acquiring timing in a reference period. The second acquired image group has acquired images obtained at an image acquiring timing in the reference period, which is delayed from the image acquiring timing of the first acquired image group by an asynchronous time. The device performs a Fourier transformation of each of a first locus and a second locus, and calculates a first frequency waveform based on the first locus and a second frequency waveform based on the second locus. The device calculates a position of the target object based on a relationship in which the frequency waveforms are delayed relative to each other by a phase corresponding to the asynchronous time.

Abstract: Some embodiments are associated with generation of a volumetric image representing an imaged object associated with a patient. According to some embodiments, tomosynthesis projection data may be acquired. A computer processor may then automatically generate the volumetric image based on the acquired tomosynthesis projection data. Moreover, distances between voxels in the volumetric image may be spatially varied.

Abstract: The method and apparatus segment parts from a main target image, represent each part as a vertex in a spanning tree, use a detector to generate a confidence map of a location of each part in a succeeding video frame and apply scale change to detector sliding windows centered about each pixel in the part location image. In the succeeding video frame, the target location is sampled and a tracking probability is generated for each part bounding box, with the tracking probability having the maximum value being selected as the location of the target in the succeeding video frame.

Abstract: Feature analysis on consecutive tissue sections (FACTS) includes obtaining a plurality of consecutive tissue sections from a tissue sample, staining the sections with at least one biomarker, obtaining a digital image thereof, and identifying one or more regions of interest within a middle of the consecutive tissue sections. The digital images of the consecutive tissue sections are registered for alignment and the one or more regions of interest are transferred from the image of the middle section to the images of the adjacent sections. Each image of the consecutive tissue sections is then analyzed and scored as appropriate. Using FACTS methods, pathologist time for annotation is reduced to a single slide. Optionally, multiple middle sections may be annotated for regions of interest and transferred accordingly.

Abstract: A method for determining a distance between two spatial points, thus between a first point and a second point, includes recording a first picture from a first viewing point, wherein the first picture includes a reference object and the first point, recording a second picture for a second viewing point, wherein the second picture includes the reference object and the second point and wherein the second viewing point is different than the first viewing point and finally determining the distance between the first point and the second point from picture data of the first picture and picture data of the second picture using a known dimension of the reference object. Thereby, the first point and/or the second point can be arranged outside a plane encompassing the reference object.

Abstract: A method and calculation unit are disclosed for reconstructing an image from measured projection data. In an embodiment, the method includes reconstructing an initial image from the projection data via back-projection; dividing the initial image into contiguous blocks of voxels; defining groups of voxels, wherein each group is defined by selecting one voxel from each block, each voxel having the same position relative to the other voxels within its block; updating the voxel values for all voxels within one group by minimizing a function consisting of a weighted sum of a first term representing the geometry of the data acquisition process, and a second regularization term; and repeating the updating of the voxel values for all voxels within one group until all groups have been updated at least once.

Abstract: An image processing apparatus and method take as input a pre-op reference image (OP) and a stream (A) of angiographic images (A1-A3). Based on multiple pre-defined regions of interest (ROIa-c) in the pre-op reference image (PO), the angiographic image best showing when displayed a respective one of the regions of interest (ROIa-c) is detected from among the stream (A) of angiographic images (A1-A3). The detected angiographic image is associated with the region of interest to form an associative data structure (DS). A graphical user interface (GUI) is generated that allows based on the associative data structure (DS) to retrieve the associated angiography upon a user selecting any one of the regions of interest (ROIa-c) on the graphical user interface (GUI).

Abstract: An iris recognition apparatus for recognizing iris in an eyeball is provided. In particular, an iris recognition apparatus including a reflection unit that reflects and transmits an image of an eyeball is provided. The reflection unit reflects and transmits an image of an eyeball. A first image collection unit collects a reflected image. A control unit extracts an iris pattern based on the collected image.

Abstract: A system for three dimensional imaging of motile objects includes an image sensor and a sample holder disposed adjacent to the image sensor. A first illumination source is provided and has a first wavelength and positioned relative to the sample holder at a first location to illuminate the sample. A second illumination source is also provided having a second wavelength, different from the first wavelength, and positioned relative to the sample holder at a second location, different from the first location, to illuminate the sample. The first and second illumination sources are configured to simultaneously, or alternatively, sequentially illuminate the sample contained within the sample holder. Three dimensional positions of the motile objects in each frame are obtained based on digitally reconstructed projection images of the mobile objects obtained from the first and second illumination sources. This positional data is connected for each frame to obtain 3D trajectories of motile objects.

Abstract: Embodiments include a system for determining cardiovascular information for a patient. The system may include at least one computer system configured to receive patient-specific data regarding a geometry of the patient's heart, and create a three-dimensional model representing at least a portion of the patient's heart based on the patient-specific data. The at least one computer system may be further configured to create a physics-based model relating to a blood flow characteristic of the patient's heart and determine a fractional flow reserve within the patient's heart based on the three-dimensional model and the physics-based model.

Abstract: A method is provided for recording a user's handwritten signature through a device including a touch-sensitive surface. The method includes a phase of obtaining a handwritten signature, which includes at least one step of acquiring the handwritten signature on the touch-sensitive surface of the device, delivering an acquired signature and at least one step of recording the acquired signature within a signature-recording space. During the phase of obtaining the handwritten signature, the method includes at least one step of measuring at least one piece of complementary data through the device and at least one step of recording the at least one piece of complementary data.

Abstract: A computer-readable map format and methods of constructing the map format are disclosed. The map format includes location information for a plurality of background objects. At least one of the background objects is a seasonal background object and the location information associated with the seasonal background object is identified during a season in which an obscuration level associated with the seasonal background object is at a minimum. The obscuration level can be based on the amount that the seasonal background object is obscured or based on the amount of obscuration caused by the seasonal background object.

Abstract: A method and system for determining a location of an occupant in a space include detecting a shape of an occupant in an image of a space; determining a location of the occupant on a floor of the space in the image, based on the shape of the occupant; and transforming the location on the floor in the image to a location of the occupant on the floor in the space.

Abstract: The present invention discloses a system and method for synthesizing a portrait sketch from a photo. The method includes: dividing the photo into a set of photo patches; determining first matching information between each of the photo patches and training photo patches pre-divided from a set of training photos; determining second matching information between each of the photo patches and training sketch patches pre-divided from a set of training sketches; determining a shape prior for the portrait sketch to be synthesized; determining a set of matched training sketch patches for each of the photo patches based on the first and the second matching information and the shape prior; and synthesizing the portrait sketch from the determined matched training sketch patches.

Abstract: An eye-fundus image output device, including circuitry to: select a site of a presented eye-fundus image, optimize an image of the selected site, output an image in which the selected site has been optimized, and generate a graphical user interface (GUI) corresponding to a received instruction, the GUI selects, as a grayscale adjustment mode, a mode in which a selected portion of an image of a predetermined range in the periphery of a designated position is optimized according to the grayscale adjustment mode.

Abstract: A method includes obtaining real-time imaging data of at least a sub-portion of an object and a region of interest therein. The method further includes displaying the real-time imaging data as the real-time imaging is obtained. The method further includes tracking extraction of a sample from the region of interest by an extraction device based on the real-time imaging data. The method further includes identifying an extraction location for the extracted sample based on the tracking and the real-time imaging data and generating a signal indicative thereof.