Abstract: Systems and methods include a reduced computation, computer-based management of point-of-care (POC) on-site ultrasound (ULS) imaging resources. At a digital computation resource of a POC site, a ULS tissue reflection sample data is received from a hand-held ULS scanning device. A digital computation resource of the POC site, applies a reduced computation tissue ULS reflection speckle noise (SN) physics model—blurring noise (BN) physics model based deep learning (DL) trained convolutional neural network (CNN) denoising process to the ULS tissue reflection sample data outputting an estimated denoised ULS tissue reflection image data. A visual rendering of the estimated denoised ULS tissue reflection image data is displayed on a display resource of the POC site.

Abstract: System, method and computer readable medium that assess characteristics of an embryo by processing video image data of the embryo. Video is obtained, typically from third parties, of a target embryo. The video has frame speed of two frames per second, or faster and includes image data representing morphokinetic movement of the embryo. The image data is processed using a trained machine learning model that assesses embryo characteristics. The video has a duration of ten minutes or less. The assessment can be a prediction of a likelihood the embryo is viable and/or will produce a pregnancy upon transfer into a recipient. Further, the assessment can predict a likelihood the embryo will: (1) produce offspring having a specific sex; (2) embody a genetic anomaly; (3) perpetuate desired traits in produced offspring and/or (4) produce undesired characteristics in produced offspring.

Abstract: An image interpretation support apparatus includes: an acquisition unit that acquires a plurality of projection images obtained by tomosynthesis imaging in which a radiation is irradiated to a breast from different irradiation angles by a radiation source and a projection image is captured at each irradiation angle by a radiation detector; a first generation unit that generates a plurality of tomographic images on each of a plurality of tomographic planes of the breast from the plurality of projection images; a second generation unit that generates a synthetic two-dimensional image from a plurality of images among the plurality of projection images and the plurality of tomographic images; a detection unit that detects an object of interest candidate region estimated to include an object of interest from the synthetic two-dimensional image; and a determination unit that determines whether or not the object of interest is included in the object of interest candidate region on the basis of the plurality of tomog

Abstract: An image processing apparatus sets a maximum size of an object that is to be included in a detection result of detection processing to detect the object from an image captured by an imaging unit, and sets a second region based on a position of a first region, designated by a user, in the image and the set maximum size. The second region, larger than the first region, includes the first region, and is subjected to the detection processing.

Abstract: The present invention relates to a deep learning-based multiple skin lesion detection system, a multiple lesion detection method, and a computer-readable recording medium that has a program for implementing same recorded thereon. The system according to the present invention enables accurate classification and detection of various skin lesions having similar characteristics, on the basis of a context-dependent decision-making structure in which the local spatial correlation between various skin lesions in skin is considered.

Abstract: An apparatus for analysing a head CT scan, where the head CT scan includes a plurality of cross-sections, includes a processor configured to select a first cross-section from among the plurality of cross-sections in the head CT scan; and analyse the first cross-section to determine whether the whole head CT scan was taken with contrast. The analyzing includes determining whether the first cross-section shows contrast, based on a presence of bright patches in the first cross-section, determining whether an amount of sulci in the first cross-section is below a threshold amount. In response to determining that the first cross-section shows contrast, determine that the whole head CT scan was taken with contrast, and in response to the determining that the first cross-section does not show contrast and that the amount of sulci is below the threshold amount determining that the whole head CT scan was taken without contrast.

Abstract: A method of reading a medical image by a computing device operated by at least one processor is provided. The method includes obtaining an abnormality score of the input image using an abnormality prediction model, filtering the input image so as not to be subsequently analyzed when the abnormality score is less than or equal to a cut-off score based on the cut-off score which makes a specific reading sensitivity; and obtaining an analysis result of the input image using a classification model that distinguishes the input image into classification classes when the abnormality score is greater than the cut-off score.

Abstract: An image processing apparatus sets a maximum size of an object that is to be included in a detection result of detection processing to detect the object from an image captured by an imaging unit, and sets a second region based on a position of a first region, designated by a user, in the image and the set maximum size. The second region, larger than the first region, includes the first region, and is subjected to the detection processing.

Abstract: A medical image processing apparatus includes a medical image acquisition unit that acquires a medical image including a subject image, a first discrimination processing unit that performs a first discrimination process of detecting a lesion and discriminating a degree of progress of the detected lesion by using a first medical image captured using first illumination light having a specific spectrum, among the medical images, and a second discrimination processing unit that performs a second discrimination process of discriminating the degree of progress of the lesion by using a second medical image captured using second illumination light having a spectrum different from the first illumination light, among the medical images.

Abstract: A system and method for generating and displaying contours. In some embodiments, the method includes: generating a respective first axial contour, of a plurality of first axial contours, for each of a first plurality of axial slices, the first axial contours defining a surface of a first volume, a first axial slice of the first plurality of axial slices including a first target point; generating a first sagittal contour in a first sagittal slice through the first target point; generating a respective second axial contour, of a plurality of second axial contours, for each of a second plurality of axial slices including the first axial slice, the second axial contours defining a surface of a second volume, a first slice of the first plurality of axial slices including a second target point; and generating a second sagittal contour in the first sagittal slice.

Abstract: A method of facilitating processing of pathology images involves receiving pathology image data representing a pathology image having a plurality of image regions, wherein the pathology image data includes, for each of the plurality of image regions, a respective plurality of representations of the image region including a first representation and a second representation, the second representation having a smaller data size than the first representation. The method involves, for each of the plurality of image regions: determining, based at least in part on the first representation of the image region, a first set of image properties, determining whether the first set of image properties meets first image property criteria, and, if the first set of image properties meets the first image property criteria, producing signals for causing the second representation to be used in place of the first representation. Other methods, systems, and computer-readable media are disclosed.

Abstract: Systems and methods are disclosed for receiving a target electronic image corresponding to a target specimen, the target specimen comprising a tissue sample of a patient, applying a machine learning system to the target electronic image to determine at least one characteristic of the target specimen and/or at least one characteristic of the target electronic image, the machine learning system having been generated by processing a plurality of training images to predict at least one characteristic, the training images comprising images of human tissue and/or images that are algorithmically generated, and outputting the target electronic image identifying an area of interest based on the at least one characteristic of the target specimen and/or the at least one characteristic of the target electronic image.

Abstract: Systems and methods are disclosed for identifying tissue specimen types present in digital whole slide images. In some aspects, tissue specimen types may be identified using unsupervised machine learning techniques for out-of-distribution detection. For example, a digital whole slide image of a tissue specimen and a recorded tissue specimen type for the digital whole slide image may be received. One or more feature vectors may be extracted from one or more foreground tiles of the digital whole slide image identified as including the tissue specimen, and a distribution learned by a machine learning system for the recorded tissue specimen type may be received. Using the distribution, a probability of the feature vectors corresponding to the recorded tissue specimen type may be computed and used as a basis for classifying the foreground tiles from which the feature vectors are extracted as an in-distribution foreground tile or an out-of-distribution foreground tile.

Abstract: Systems and methods are disclosed for identifying tissue specimen types present in digital whole slide images. In some aspects, tissue specimen types may be identified using unsupervised machine learning techniques for out-of-distribution detection. For example, a digital whole slide image of a tissue specimen and a recorded tissue specimen type for the digital whole slide image may be received. One or more feature vectors may be extracted from one or more foreground tiles of the digital whole slide image identified as including the tissue specimen, and a distribution learned by a machine learning system for the recorded tissue specimen type may be received. Using the distribution, a probability of the feature vectors corresponding to the recorded tissue specimen type may be computed and used as a basis for classifying the foreground tiles from which the feature vectors are extracted as an in-distribution foreground tile or an out-of-distribution foreground tile.

Abstract: A system and method of face recognition comprising multiple phases implemented in a parallel architecture. The first phase is a normalization phase whereby a captured image is normalized to the same size, orientation, and illumination of stored images in a preexisting database. The second phase is a feature extraction/distance matrix phase where a distance matrix is generated for the captured image. In a coarse recognition phase, the generated distance matrix is compared with distance matrices in the database using Euclidean distance matches to create candidate lists, and in a detailed recognition phase, multiple face recognition algorithms are applied to the candidate lists to produce a final result. The distance matrices in the normalized database may be broken into parallel lists for parallelization in the feature extraction/distance matrix phase, and the candidate lists may also be grouped according to a dissimilarity algorithm for parallel processing in the detailed recognition phase.

Abstract: An estimation method for estimating a parameter related to skin function is provided. The estimation method includes an image acquisition step for acquiring a skin image in which unevenness of a skin surface is captured; an extraction step for extracting a feature vector based on topological information on the skin image from the skin image acquired in the image acquisition step; an estimation step for estimating the parameter related to skin function based on the feature vector extracted in the extraction step, using an estimation model constructed based on past actual measurement data in which feature vectors are associated with the parameter related to skin function; and a presentation step for presenting the parameter related to skin function estimated in the estimation step.

Abstract: The invention provides methods and systems for generating an ultrasound image. In a method, the generation of an ultrasound image comprises: obtaining channel data, the channel data defining a set of imaged points; for each imaged point: isolating the channel data; performing a spatial spectral estimation on the isolated channel data; and selectively attenuating the spatial spectral estimation channel data, thereby generating filtered channel data; and summing the filtered channel data, thereby forming a filtered ultrasound image. In some examples, the method comprises aperture extrapolation. The aperture extrapolation improves the lateral resolution of the ultrasound image. In other examples, the method comprises transmit extrapolation. The transmit extrapolation improves the contrast of the image. In addition, the transmit extrapolation improves the frame rate and reduces the motion artifacts in the ultrasound image. In further examples, the aperture and transmit extrapolations may be combined.

Abstract: A method and an apparatus for automatic muscle segmentation are provided. The method includes receiving a high-resolution three-dimensional (3D) image obtained by a magnetic resonance imaging (MM) system and splitting the high-resolution 3D image into high-resolution 3D sub-images. Furthermore, the method includes acquiring low-resolution 3D sub-images of the high-resolution 3D sub-images and determining a boundary box within each corresponding low-resolution 3D sub-image. Moreover, the method includes determining a crop box for each boundary box, cropping each high-resolution 3D sub-image based on its corresponding crop box, and segmenting at least one muscle from the cropped box high-resolution 3D sub-image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining a subset of brain data of a patient. One of the methods comprises providing connectivity data for presentation to a user, the connectivity data characterizing, for each pair of parcellations comprising a first parcellation and a second parcellation from a plurality of parcellations, a degree of correlation between the brain activity of the first parcellation and the brain activity of the second parcellation in the brain of a patient; determining one or more elements of interest in the connectivity data; determining one or more parcellations associated with elements of interest in the connectivity data; obtaining brain atlas data; determining a subset of the brain atlas data associated with the determined parcellations; and providing the subset of the brain atlas data to a user device for rendering the subset to the user.

Abstract: Provided are a method for processing automobile image data, an apparatus, and a readable storage medium. The method includes training a preset adversarial network according to automobile image sample data obtained by collecting and preset random noise information, to obtain a trained adversarial network for generating automobile image data; and inputting the automobile image sample data into the trained adversarial network, and generating the automobile image data including a variety of the random noise information, according to a preset generation target, wherein the automobile image data are configured to train an automobile image recognition neural network to perform automobile image recognition. Therefore, the automobile image data that may be used to train an automobile image recognition neural network are generated by using the adversarial network, which amplifies the amount of data, and reduces the cost of obtaining data.