Abstract: In many medical image classification problems, distinctive image features are often localized in certain anatomical regions. The key to efficient and accurate classification in such problems is the localization of the region of interest (ROI). To address this problem, a multi-atlas label fusion technique was developed for automatic ROI detection. Given training images with class labels, the present method infers voxel-wise scores for each image showing how distinctive each voxel is for categorizing the image. The present method for ROI segmentation and for class specific ROI patch extraction in a 2D cardiac CT body part classification application was applied and shows the effectiveness of the detected ROIs.

Abstract: A method and system that allows healthcare providers, hospitals, skilled nursing facilities and other persons to monitor disabled, elderly or other high-risk individuals to prevent or reduce falls and/or mitigate the impact of a fall by delivering automated notification of “at risk” behavior and falls by such an individual being monitored where assistance is required. Two systems are used to identify patients, a skeletal tracking system, which identifies patients by biometric indicators, and a virtual blob detection system. In the virtual blob system, the monitored individual is virtually represented as a blob object of at least a specific size by a computerized monitoring system and such system detects and alerts when the blob object enters or crosses into a virtually defined or designated blob detection zone and remains in the zone for at least a predetermined period of time. These systems may be used concurrently, or one system may be used primarily, with the other system acting as a failsafe.

Abstract: The invention relates to an image analysis method for automatically extracting data from a bar chart. A processor receives a digital image of a bar chart comprising a plurality of o-bars. The processor provides a plurality of hypothesis charts respectively specifying a sequence of h-bars, a particular way of grouping the h-bars into categories, and an injective mapping from the o-bars to the h-bars. The processor compares the h-bars of the hypothesis charts with the o-bars of the bar chart in the image for assigning the o-bars to series and categories in accordance with the one of the hypothesis charts whose h-bars are most similar to the o-bars and for returning the series and the category assigned to said o-bars.

Abstract: One aspect of the present invention discloses a watermark embedding method. The method includes: inputting an original bitstream; determining a first frame for embedding a watermark in the input original bitstream; selecting one of frames after the first frame as a second frame; generating the first frame a bidirectional-coded frame (B frame) referring to the second frame; generating the second frame as a reference frame of the first frame; and embedding the watermark in the first frame generated as the B frame.

Abstract: Various embodiments are described herein for methods, devices and systems that can be used to determine a breast density value from an input image of patient's breast. In one example embodiment, the breast density value is calculated by receiving an input image corresponding to the digital mammogram, removing metadata information from the input image to generate an intermediate image, generating a region of interest (ROI) image based on the intermediate image, extracting values for predictor variables based on the metadata information, the intermediate image and the ROI image, and calculating breast density based on the values of the predictor variables. The breast density value is calculated based on a breast density model.

Abstract: Embodiments disclosed herein are directed, among other things, to imaging systems, methods, and apparatuses for automatically identifying fields of view (FOVs) for regions in an image encompassing tumor are disclosed. In embodiments and in further aspects of the present invention, a computer-implemented method is disclosed for a tumor region based immune score computation. The method, in accordance with the present invention, involves identifying regions, for example, tumor areas or regions around a tumor area, partitioning a whole slide image or portion of a whole slide image into multiple regions related to the tumor, selecting FOVs within each identified region, and computing a number of cells present in each FOV. An immune score and/or immune-related score may be generated based on the cells counted in each FOV.

Abstract: A method for reducing image disturbances caused by reconstructed defective pixel clusters located in signal-gradient affected diagnostic image regions. An individually adapted central symmetrical pair reconstruction (CSP) kernel is composed for a defective image pixel based on a kernel-pair candidate order encoded in a model thereby using the pixel's validity state. The image impacted by defective pixels is corrected in real-time by statistical filtering or spatial convolution of the kernel-associated image data accessible via a predetermined CSP kernels image-offsets structure.

Abstract: A method for decoding a picture on an electronic device is described. The method includes obtaining a bitstream. The method also includes obtaining a current picture. The method further includes obtaining a relative reference picture set (RPS) parameter. The method additionally includes initializing an index value. Furthermore, the method includes processing another RPS parameter based on the index value. The method also includes decoding the current picture.

Abstract: In the image processing apparatus, the image processing method, and the recording medium of the invention, an image analysis unit analyzes the contents of each of a plurality of images acquired by an image acquisition unit, and an evaluation value calculation unit calculates an analysis evaluation value of each image based on the analysis result of each image. A group forming unit forms one or more groups, each of which includes a plurality of similar images, by specifying similar images among the plurality of images. The evaluation value calculation unit calculates an overall evaluation value by adding a value to an analysis evaluation value of each of the plurality of similar images based on evaluation information, which indicates high evaluation for the plurality of similar images, for each of the groups.

Abstract: The invention relates to a method for detecting persons and/or objects in a space using a depth map to be analyzed, comprising a step for detecting the head and shoulders of any people who may be present in the depth map to be analyzed.

Abstract: A method for decoding a picture on an electronic device is described. The method includes obtaining a bitstream. The method also includes obtaining a current picture. The method further includes obtaining a relative reference picture set (RPS) parameter. The method additionally includes initializing an index value. Furthermore, the method includes processing another RPS parameter based on the index value. The method also includes decoding the current picture.

Abstract: A medical observation system includes: a position information storage portion configured to perform processing for storing first position information indicating an initial position of an object for executing treatment in a three-dimensional image generated using a plurality of tomographic images of a subject; a movement detection portion configured to detect movement of the object; a position information acquisition portion configured to acquire second position information indicating a present position of the object in the three-dimensional image when the movement of the object is detected; and a display image generation portion configured to update a position of the object in the three-dimensional image from the first position information to the second position information in a case that the second position information is acquired, and generate an image superimposed on the three-dimensional image or on a pseudo fluoroscopic image generated based on the plurality of tomographic images.

Abstract: Methods and systems are presented for obtaining photographic data recently taken via one or more airborne vehicles (drones, e.g.) and for prioritizing forestry-related review and decision-making as an automatic response to the content of the photographic data even where remote decision-makers are only available via limited-bandwidth connections.

Abstract: This invention describes methods and systems for use of computer vision systems for classification of biological cells as an aid in disease diagnostics. More particularly the present invention describes a process comprising employing a robust and discriminative color space which will help provide segmentation of the cells; employing a segmentation algorithm, such as a feature-based level set, that will be able to segment the cells using a different k-phase-segmentation process, which detect for example, if a while blood cell occurs for segmenting the internal components of the cell robustly; employing a combination of different type of features including shape, texture, and invariant information, and employing a classification step to associate abnormal cell characteristics with disease states.

Abstract: Systems and methods are described for automatically identifying a food item. A color image and a thermal image are received by an electronic processor with a first food item in the field of view of both the color image and the thermal image. The electronic processor identifies a region of pixels in the color image that corresponds to the first food item based at least in part on a temperature intensity of the pixels in the identified region of pixels relative to other pixels in the thermal image. At least one feature is extracted from the identified region of pixels in the color image corresponding to the first food item and the electronic processor automatically identifies a type of food corresponding to the first food item based at least in part on the at least extracted feature.

Abstract: The present disclosure provides a navigation method based on a three-dimensional scene, comprising: calculating an interest value of a viewpoint of a camera based on heights, volumes, irregularities and uniqueness of buildings in a scene; generating trajectory parameters of the camera according to the interest value of the viewpoint, so as to navigate according to the trajectory parameters. The navigation method based on a three-dimensional scene of the present disclosure obtains a reasonable interest value of the viewpoint based on heights, volumes, irregularities and uniqueness of the buildings, thereby achieving a high-quality navigation.

Abstract: Systems and methods for tomographic reconstruction of an image include systems and methods for producing images from k-space data. A k-space data set of an imaged object is acquired using know k-space data acquisition systems and methods. A portion of the k-space data set is sampled so as to collect some portion of the k-space data. An image is then reconstructed from the collected portion of the k-space data set according to a convex optimization model.

Abstract: A method of treating cardiac arrhythmia in a heart, including (i) determining that cardiac tissue is viable but with reduced innervation; and (ii) ablating the tissue to reduce a prevalence of arrhythmia in said heart. Optionally, the determining comprises detecting portions of heart wall which lack electrical activity. Optionally, at least some tissue which is viable but lacks nervous control is ablated, for example, to reduce or avoid arrhythmia.

Abstract: A method for identifying biomarker-positive tumor cells is disclosed. The method includes, for example, reading a first digital image and a second digital image into memory, the first and second digital image depicting the same area of a first slide; identifying a plurality of nuclei and positional information of said nuclei by analyzing the light intensities in the first digital image; identifying cell membranes which comprise the biomarker by analyzing the light intensities in the second digital image and by analyzing the positional information of the identified nuclei; and identifying biomarker-positive tumor cells in said area, wherein a biomarker-positive tumor cell is a combination of one identified nucleus and one identified cell membrane that surrounds the identified nucleus.

Abstract: A method of generating a patient specific prosthetic implant is described, which includes: generating a three dimensional electronic representation of a human anatomical feature of a unique patient; identifying one or more representative surface curvature features on the three dimensional electronic representation; and associating the three dimensional electronic representation with a virtual implant template of the human anatomical feature selected from a database of virtual implant templates, and comparing fit of the identified representative surface curvature features of the three dimensional electronic representation with corresponding surface curvature features of the virtual implant template. The virtual implant template is selected to have the most similar corresponding surface curvature features.