Abstract: Methods and systems for determining a diagnostically unacceptable medical image. One system includes at least one electronic processor configured to receive a new medical image captured via a medical imaging device. The at least one electronic processor is also configured to determine a classification of the new medical image using a model developed with machine learning using training information that includes a plurality of medical images and an associated classification for each medical image, each associated classification identifying whether the associated medical image is diagnostically unacceptable, wherein the classification of the new medical image indicates whether the new medical image is diagnostically unacceptable.

Abstract: The present disclosure describes methods, devices, and storage medium for recognizing a target object in a target image. The method including obtaining, by a device, an image recognition instruction, the image recognition instruction carrying object identification information used for indicating a target object in a target image. The device includes a memory storing instructions and a processor in communication with the memory. The method includes obtaining, by the device, an instruction feature vector matching the image recognition instruction; obtaining, by the device, an image feature vector set matching the target image, the image feature vector set comprising an ith image feature vector for indicating an image feature of the target image in an ith scale, and i being a positive integer; and recognizing, by the device, the target object from the target image according to the instruction feature vector and the image feature vector set.

Abstract: An artificial intelligence (AI) system for determining to which social group a person belongs. The AI system includes a computer system and a computer program product which, when running on the computer system, is to: retrieve at least one image of the person belonging to a social group; labels the person, resulting in a labeled person; retrieve at least one image part showing appearance of the labeled person; subject said at least one image part to at least one trained machine learning model defined in the computer program product, the machine learning model including at least a part that is trained on a test set of annotated images which are annotated with respect to categories that correlate to social group, and determine from the at least one trained machine learning model a social group category to which the labeled person belongs.

Abstract: Systems and methods are disclosed for using an integrated computing platform to view and transfer digital pathology slides using artificial intelligence, the method including receiving at least one whole slide image in a cloud computing environment located in a first geographic region, the whole slide image depicting a medical sample associated with a patient, the patient being located in the first geographic region; storing the received whole slide image in a first encrypted bucket; applying artificial intelligence to perform a classification of the at least one whole slide image, the classification comprising steps to determine whether portions of the medical sample depicted in the whole slide image are healthy or diseased; based on the classification of the at least one whole slide image, generating metadata associated with the whole slide image; and storing the metadata in a second encrypted bucket.

Abstract: This disclosure describes techniques that include generating, based on a description of a scene, a movie or animation that represents at least one possible version of a story corresponding to the description of the scene. This disclosure also describes techniques for training a machine learning model to generate predefined data structures from textual information, visual information, and/or other information about a story, an event, a scene, or a sequence of events or scenes within a story. This disclosure also describes techniques for using GANs to generate, from input, an animation of motion (e.g., an animation or a video clip). This disclosure also describes techniques for implementing an explainable artificial intelligence system that may provide end users with information (e.g., through a user interface) that enables an understanding of at least some of the decisions made by the AI system.

Abstract: Techniques for the modification of at least part of a target image (e.g., scene objects within the target image), e.g., to make the target image appear that it was captured at a different time (e.g., a different time of day, different time of year) are disclosed. This “dynamic re-timing” of the target image may be achieved by finding one or more source images including the same (or similar) scene depicted in the target image (but, e.g., captured at different times), extracting stylistic elements from the source image(s), and then modifying at least part of the target image in a realistic fashion (e.g., not altering the geometry of objects in the target image), based on one or more extracted stylistic elements from the source image(s). Three-dimensional modeling of scene objects may allow a more realistic-looking transfer of the extracted stylistic elements onto scene objects in the target image to be achieved.

Abstract: Use of augmented reality to provide a real-time two-dimensional representation of medical imaging data to a user in a three-dimensional space. An augmented reality system is discussed that may provide a single stage processing for video data ingestion directly from a video data output of a medical imaging device. In turn, latency in the resulting video data presented to the user via an augmented reality display may be reduced. The augmented reality system may also allow for a high degree of control over the virtual position, rotation, size, and/or opacity of the two-dimensional representation of the video data in the three-dimensional space associated with the augmented reality system.

Abstract: A method for machine learning based ultrasound image reconstruction can include receiving, at a reconstruction engine, imaging data; generating an initial estimate for a transmission image via a neural network trained (machine or self-learning) on paired transmission ultrasound and reflection ultrasound data; and performing image reconstruction using the initial estimate to generate transmission ultrasound images. The image reconstruction can generate higher quality transmission ultrasound when carried out by using the initial estimate as the starting point for iterative image reconstruction and using transmission data obtained via conventional transmission ultrasound frequencies (e.g. from 0.8 MHz to 1.5 MHz).

Abstract: Systems and methods for visualizing, and/or determining the amount of, collagen and elastin in tissue are provided. Training data can be generated using Mueller matrix polarimetry microscopy data, combined with second harmonic generation (SHG) and/or two photon excitation fluorescence (TPEF) microscopy data as ground truth. The SHG and/or TPEF data can be used to train a neural network for feature extraction, and classification can be performed. The components and decompositions of the Mueller matrix data can be arranged as individual channels of information, forming one voxel per sample.

Abstract: A method for using machine learning to perform classification of anatomical coverage of images includes acquiring a series of medical images of a subject. The method also includes automatically, with a computer system, analyzing each image in the series of medical images using a machine-learning technique to classify each image in the series of medical images based on anatomical structures reflected in each image in the series of medical images.

Abstract: The present disclosure includes methods of assessing a histologically stained specimen based on a determined color signature of a region of interest of the specimen. Such assessments may be performed for a variety of purposes including but not limited to assessing the quality of the histological stain, as part of identifying one or more biologically relevant features of the image, as part of differentiating one feature of the image from other features of the image, identifying an anomalous area of the stained specimen, classifying cells of the specimen, etc. Also provided are systems configured for performing the disclosed methods and computer readable medium storing instructions for performing steps of the disclosed methods.

Abstract: The instant disclosure provides methods of extracting stain-independent features from digital images of histologically stained cells. Stain-independent features provide consistent assessment of cell morphology in the presence of staining variation and across different stains or stain formulations. Improved consistency in cell morphology assessments finds use in automated cell classification and other image processing applications. Also included are systems for practicing the described methods. The instant disclosure also provides computer readable media storing instructions that, when executed by a computing device, cause the computing device and/or components of a described system to perform steps of a method involving of extraction of stain-independent features from digital images.

Abstract: A non-invasive computer-aided diagnosis system generates a diagnosis of mild cognitive impairment, a disease state which often leads to the development of Alzheimer's disease. The system uses as inputs both functional positron emission tomography and structural magnetic resonance imaging data, reconstructs a model of the patient's cortex, uses machine-learning techniques to generate probabilities for mild cognitive impairments for local cortical regions, uses machine-learning techniques to fuse the local diagnoses to generate a global diagnosis based on each imaging modality, then uses machine-learning techniques to fuse the modality-specific global diagnoses to generate a final global diagnosis.

Abstract: The present disclosure provides a dynamic tone mapping method, a mobile terminal, and a computer readable storage medium. The method includes: acquiring maximum brightness information and average brightness information of a frame to be displayed on the display terminal; inquiring a tone mapping data group respectively corresponding to the maximum brightness information and the average brightness information in a preset tone mapping look-up table; and calling the tone mapping data group and transforming a tone mapping on the frame to be displayed on the display terminal. The present disclosure can change the tone mapping data group for transforming the tone mapping in real time according to the maximum brightness information and the average brightness information of the frame monitored in real time, to reasonably utilize the hardware dynamic range and present a better HDR effect.

Abstract: Systems and methods for automatically identifying and characterizing one or more lanes in image data for one or more electrophoresed samples. The method includes receiving data representing an image of one or more electrophoresed samples, segmenting the data into one or multiple data segments or portions within a region of interest (ROI), wherein the one or multiple data segments represent (e.g., when visually displayed) one or multiple lane segments along a first axis in the ROI, each of the one or multiple lane segments traversing one or multiple lanes in the image data, generating an intensity profile for at least a first data segment of the one or multiple data segments along a second axis orthogonal to the first axis, and processing the intensity profile to determine a location and parameters for each of one or multiple lanes in the first data segment.

Abstract: An image processing apparatus includes a processor including hardware, the processor being configured to extend an N-bit color video signal to an M (M>N)-bit color video signal, subject the M-bit color video signal obtained by the extension to level correction based on (M?N), and subject the color video signal subjected to the level correction to white balance correction.

Abstract: Technologies are disclosed for efficiently identifying objects in videos using deep neural networks and motion information. Using the disclosed technologies, the amount of time required to identify objects in videos can be greatly reduced. Motion information for a video, such as motion vectors, are extracted during the encoding or decoding of the video. The motion information is used to determine whether there is sufficient motion between frames of the video to warrant performing object detection on the frames. If there is insufficient movement from one frame to a subsequent frame, the subsequent frame will not be processed to identify objects contained therein. In this way, object detection will not be performed on video frames that have changed minimally as compared to a previous frame, thereby reducing the amount of time and the number of processing operations required to identify the objects in the video.

Abstract: A system and method are provided for optimizing histogram cumulative distribution function curves. In use, a first image is received and divided into two or more pixel regions. For at least one of the two or more pixel regions, a first histogram is computed, and based on the first histogram, at least one cumulative distribution function is computed for the at least one of the two or more pixel regions. Next, based on the at least one cumulative distribution function, two or more curve fit coefficients are extracted and interpolated. Further, an interpolated cumulative distribution function is created based on the interpolation and the interpolated cumulative distribution function is applied to the at least one of the two or more pixel regions.

Abstract: Systems and methods are disclosed for generating a specialized machine learning model by receiving a generalized machine learning model generated by processing a plurality of first training images to predict at least one cancer characteristic, receiving a plurality of second training images, the first training images and the second training images include images of tissue specimens and/or images algorithmically generated to replicate tissue specimens, receiving a plurality of target specialized attributes related to a respective second training image of the plurality of second training images, generating a specialized machine learning model by modifying the generalized machine learning model based on the plurality of second training images and the target specialized attributes, receiving a target image corresponding to a target specimen, applying the specialized machine learning model to the target image to determine at least one characteristic of the target image, and outputting the characteristic of the tar

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing a critical edge detection neural network and a geometric model to determine camera parameters from a single digital image. In particular, in one or more embodiments, the disclosed systems can train and utilize a critical edge detection neural network to generate a vanishing edge map indicating vanishing lines from the digital image. The system can then utilize the vanishing edge map to more accurately and efficiently determine camera parameters by applying a geometric model to the vanishing edge map. Further, the system can generate ground truth vanishing line data from a set of training digital images for training the critical edge detection neural network.