Abstract: An excrement judgement system according to the embodiment including: an acquisition unit that acquires image information on an image in which excrement excreted in a defecation action per time is captured; a determination unit that determines properties of a plurality of stools included in the image information and stool amounts corresponding to the properties of the plurality of stools; and an outputting unit that associates the properties of the plurality of stools and the stool amounts corresponding to the properties of the plurality of stools that are determined by the determination unit, and outputs the associated properties and stool amounts to a device to be displayed.

Abstract: The present disclosure relates to a system and method (10) for monitoring a set-up for manufacture and/or setting up for manufacture and/or tearing down after manufacture of a biopharmaceutical product. The method comprises: processing (S2, S3, S4) at least one image of a scene comprising the set-up for manufacture of the biopharmaceutical product. The processing of the at least one image comprises performing (S2) a first process on the at least one image for classifying first objects in the image, said first objects being devices such as clamps, pumps, valves and/or sensors and/or any other bio processing equipment. The first process comprising identifying, localizing and classifying the first objects in the image. A second process is performed (S3) on the at least one image for identifying and localizing connections in the images.

Abstract: A system and method configured to better identify patient-specific anatomical landmarks, measure anatomical parameters and features, and predict the patient's need for surgery within a predetermined time period. In some embodiments, the system and method is configured to predict the likelihood or risk that a patient will require total hip arthroplasty. In some embodiments, the present invention includes machine learning technology Some embodiments of the present invention include a first ML machine configured to received medical images as inputs and identify anatomical landmarks as outputs; a measurement module to measure joint space width, hip dysplasia angles, and/or leg length differential; and a second ML machine configured to receive the anatomical measurements and patient demographic data as inputs and produce a risk or likelihood that the patient will require surgery within a certain time frame.

Abstract: Systems and methods for scan preparation are provided. The systems may obtain a first parameter set of a subject to be scanned by a medical device acquired before a scan is performed on the subject. The first parameter set may relate to a physiological motion of the subject acquired before the scan is performed on the subject. The systems may predict, based on the first parameter set and an estimation model, a second parameter set of the subject. The second parameter set may relate to the physiological motion of the subject. The systems may determine at least one scan parameter for the scan based at least in part on the second parameter set. The systems may cause the medical device to perform the scan on the subject based on the at least one scan parameter.

Abstract: An apparatus for robotic surgery comprises a processor configured with instructions to receive patient data from treated patients, receive surgical robotics data for each of the plurality of treated patients, and output a treatment plan of a patient to be treated in response to the patient data and the surgical robotics data. This approach has the advantage of accommodating individual variability among patients and surgical system parameters so as to provide improved treatment outcomes.

Abstract: Embodiments consistent with the present disclosure provide systems, methods, and devices for providing wound capturing guidance. In one example, consistent with the disclosed embodiments, an example system may: display, on a mobile device, a user interface configured to guide a patient through one or more steps for performing a medical action, the plurality of steps including at least: using at least one item of a medical kit; and capturing at least one image of at least part of the at least one item of the medical kit using at least one image sensor associated with the mobile device. The example system may also: detect a failure to successfully complete the medical action; select from one or more alternative reactions, a reaction to the detected failure likely to bring a successful completion of the medical action; and provide instructions associated with the selected reaction.

Abstract: Embodiments of the present disclosure provide a method and system for co-operative and cascaded inference on the edge device using an integrated Deep Learning (DL) model for object detection and localization, which comprises a strong classifier trained on largely available datasets and a weak localizer trained on scarcely available datasets, and work in coordination to first detect object (fire) in every input frame using the classifier, and then trigger a localizer only for the frames that are classified as fire frames. The classifier and the localizer of the integrated DL model are jointly trained using Multitask Learning approach. Works in literature hardly address the technical challenge of embedding such integrated DL model to be deployed on edge devices. The method provides an optimal hardware software partitioning approach for components or segments of the integrated DL model which achieves a tradeoff between latency and accuracy in object classification and localization.

Abstract: Disclosed are a computer-implemented method, a system and a computer program product for feature processing. In the computer-implemented method for feature processing, two input features selected from multiple features of each sample in a sample set are projected to one resulting feature by one or more processing units based on a specified curve. The sample set is updated by replacing the two input features with the one resulting feature for each sample in the sample set by one or more processing units. The projecting and the updating for the sample set are repeated by one or more processing units until the number of features of each sample in the sample set reaches a predetermined criterion.

Abstract: The present invention provides a graph-based prostate diagnosis network (GPD-Net) and a method for using the same to predict a prostate health status of a patient from a 3D magnetic resonance imaging (MRI) scan containing a plurality of 2D MRI slices. The GPD-Net only demands patient-level annotations of MRI scan for training by formulating the diagnosis task of 3D prostate MRI scan in a multi-instance learning (MIL) strategy, and regarding each 2D MRI slice in the 3D prostate MRI scan as an instance. The GPD-Net includes a plurality of importance-guided graph convolutional layers to explore the diagnostic information with the importance-based topology. The present invention provides accurate prediction of prostate diseases and achieve more reliable diagnosis from MRI scans, therefore can effectively alleviate the workload of clinician in viewing the slices of MRI scan.

Abstract: Image co-registration entails: emitting energy, and responsively and dynamically acquiring images, the acquired images having a given dimensionality; selecting, repeatedly, and dynamically with the acquiring, from among the acquired images and, as a result of the selecting, changing, repeatedly, and dynamically, membership in a set of images of the given dimensionality; and, synchronously with the change, dynamically and iteratively registering the set to an image having a dimensionality higher than the given dimensionality. The co-registration is realizable with an imaging probe for the acquiring, and a tracking system for tracking a location, and orientation, of the probe, the registering being specialized for the acquiring with the probe being dynamically, during the acquiring, any one or more of angulated, rotated and translated.

Abstract: A portable device for quality control of semen having a housing and within an inner space of the housing, a battery, a processor and a sample storing device for fixing a sample transporting cell. The device further has a microscope having a camera secured to the housing, an optical device connected to the camera and a light source illuminating the sample transporting cell during use. The sample storing device is arranged in the upper side of the housing or adjacent thereto. The light source is arranged on the outer side of the sample storing device and connected to the housing. The camera is arranged in the inner space of the housing, on the inner side of the sample storing device such that the distance between the supporting plane of the sample storing device and the light sensor of the camera is at most 35 mm.

Abstract: A diagnostic tool and methods of using the tool are provided to quantify an amount of nasal collapse in a patient. The diagnostic tool includes a mask with an endoscope port and an opening to allow air flow, an endoscope with a camera adapted to take an image of the nasal valve, and an air flow sensor adapted to measure an inhalation rate of the patient. The diagnostic tool can quantify a size difference between the nasal valve during inhalation and zero flow by calculating a percentage difference in an area or one or more dimensions of the nasal valve during inhalation and zero flow.

Abstract: An information processing apparatus according includes an acquisition unit configured to acquire an image, an extraction unit configured to extract part of regions included in the image as a target region, a determination unit configured to determine a variation in density value of a pixel included in the target region such that an absolute value of the variation in density value of the pixel included in the target region is larger than an absolute value of a variation in density value of a pixel included in a region other than the target region, a generation unit configured to generate a training image in which a density value of the pixel included in the target region is changed based on the variation determined by the determination unit, and a training unit configured to train a identifier using the training image.

Abstract: A method for segmenting a 3D model image of a patient's dentition obtains a first 3D model image of the patient dentition and obtains a first segmentation of the first 3D model image, wherein the first segmentation provides at least a tooth surface contour and a tooth label for one or more teeth of the first 3D model. A second 3D model image of the patient dentition is obtained. Each segmented tooth surface contour of the first 3D model is registered to corresponding tooth surface contour of the second 3D model. A second segmentation of the second 3D model image is obtained according to the registered tooth surface contour, wherein the second segmentation similarly provides at least tooth surface contour and a tooth labeling for one or more teeth of the second 3D model image. The segmented second 3D model image is displayed, transmitted, or stored.

Abstract: Machine vision systems and methods for automatically generating machine vision job(s) based on region of interests (ROIs) of digital images are disclosed herein. The systems and methods comprise configuring a machine vision tool for capturing an image ID depicted in training images and labeling each training image to indicate a success or failure status of an object depicted by the training images. Candidate image feature(s) are extracted from the training images for generation of candidate ROI(s). A training set of ROIs are selected from the candidate ROI(s) and are designated as an included or excluded ROIs. The training set of ROIs and the training images are used to train a vision learning model configured to output a machine vision job deployable to an imaging device that implements the machine vision job to detect the success or failure statuses of additional image(s) depicting the object.

Abstract: A medical image processing device includes: a first captured image acquisition unit configured to acquire a first left-eye image and a first right-eye image; a second captured image acquisition unit configured to acquire a second left-eye image and a second right-eye image; a superimposed image generation unit configured to superimpose corresponding pixels of the first left-eye image and the second left-eye image on each other to generate a left-eye fluorescence superimposed image and superimpose corresponding pixels of the first right-eye image and the second right-eye image on each other to generate a right-eye fluorescence superimposed image; and a display controller configured to generate a display image from the first left-eye and right-eye images, the second left-eye and right-eye images, the left-eye and the right-eye fluorescence superimposed images, wherein the display image includes a stereoscopically observable three-dimensional fluorescence superimposed image generated from the left-eye and the ri

Abstract: First and second predictors are used to identify regions of interest in a medical image. The first predictor is configured to maximize precision in identifying one or more abnormalities that it was trained to recognize, or at least to have greater precision than the second predictor. The second predictor is configured or selected to maximize sensitivity (i.e., recall) in identifying one or more abnormalities that it was trained to recognize, or at least to have greater sensitivity than the first predictor. The predictions of the first and second predictors may be used to create a digital map image showing the locations of regions of interest identified by the first and second predictors. Alternatively or in addition, the predictions may be used to rank images or image sets in terms of review priority.

Abstract: An example system for microvascular assessment of a patient can include: a fundus imaging device including: a camera configured to capture one or more images of an eye of the patient; and at least one light source; and a microvascular assessment computing device including: a processor; and memory encoding instructions which, when executed by the processor, cause the system to: activate the light source to direct light at a fundus of the eye of the patient; capture, with the camera, one or more images of the fundus of the patient, the fundus comprising a plurality of blood vessels; and analyze with the microvascular assessment computing device, the one or more images to determine a microvasculature health index for the patient.

Abstract: A CPU acquires a distance image which indicates a distance to an imaging target and is captured by a TOF camera that captures the distance image using, as the imaging target, a mammography apparatus which is an abnormality determination target. In addition, the CPU acquires reference distance image as reference distance information related to a reference value of a distance between the abnormality determination target in a reference state and the TOF camera. Further, the CPU performs determination on an abnormality appearing in an outward appearance of the abnormality determination target on the basis of the distance image and the reference distance image.

Abstract: An integrated system for processing and using images acquired of subjects in a research or clinical environment is provided. The integrated system includes an image and data bank, a workflow management module, a cloud storage module and a pre-processing module. The pre-processing engine is positioned between the workflow management module and the cloud storage module and is configured to receive raw images, data associated with the raw images and the data associated with the imaged subjects from the workflow management module and process this data and provide the processed data to be pushed into the cloud storage module. The pre-processing engine also anonymizes the data to provide de-identified images and data to the cloud storage module and creates a key that relates the raw images, data associated with the raw images and the data associated with the imaged subjects to the de-identified, processed images and data. The key remains separate and un-connected from the de-identified, processed images and data.

Abstract: An ultrasound imaging method and system. The method comprises: for each of a plurality of steer angles, including a reference steer angle, transmitting acoustic energy to a target region at the particular steer angle, receiving acoustic reflections, and converting the acoustic reflections to an image, with the image being associated with the particular steer angle; computing motion information based on the image associated with the reference steer angle; and generating a compounded ultrasound image based on the image associated with each of the plurality of steer angles and based on the motion information.

Abstract: A medical information processing system according to an embodiment includes processing circuitry and a display. On the basis of one of the type of at least one abnormality detection algorithm to which a medical image related to an examined subject is to be input and information relevant to an abnormality detected by inputting the medical image to the abnormality detection algorithm, the processing circuitry judges whether or not urgency is present in a disorder related to the abnormality. When it is determined that the urgency is present, the display displays, in an examination list of examination orders, assessment information related to assessing the abnormality and urgency information indicating the urgency so as to be positioned adjacent to any of the examination orders related to the abnormality.

Abstract: There is disclosed a system and method for diagnosing plagiocephaly (flat head syndrome, associated primarily with in infants) from photographs of the head. The method and apparatus may involve the use of a processor circuit, for example an application server, for automatically identifying the contour of the head in a plurality of images, then computing geometrical measurements in order quantify plagiocephaly. Photographs are acquired from an overhead view of a head, where the images may be rotated manually or automatically to a standard orientation. For each image, an optimal head contour is identified as minimizing a mathematical cost function combining local image filter responses designed for edge detection and a global model of head contour shape combining smoothness and convexity constrains. Length measurements are then computed from the identified contour, e.g. head diameter, diagonal diameter, and used to quantify the degree of head asymmetry and diagnose plagiocephaly.

Abstract: A method and apparatus of generating a modified segmented structure is disclosed. This modified segmented structure subtracts pixels or voxels in an inward direction from the segmented structure to create a smaller volume or area than the segmented structure. Analysis of the smaller volume can be useful in generating custom volumes, which can then be processed to improve visualization inside the custom volume.

Abstract: A computerized system and method of modeling myocardial tissue perfusion can include acquiring a plurality of original frames of magnetic resonance imaging (MRI) data representing images of a heart of a subject and developing a manually segmented set of ground truth frames from the original frames. Applying training augmentation techniques to a training set of the originals frame of MRI data can prepare the data for training at least one convolutional neural network (CNN). The CNN can segment the training set of frames according to the ground truth frames. Applying the respective input test frames to a trained CNN can allow for segmenting an endocardium layer and an epicardium layer within the respective images of the input test frames. The segmented images can be used in calculating myocardial blood flow into the myocardium from segmented images of the input test frames.

Abstract: Disclosed are an image matching method, an image matching device, and a storage medium. A first image sequence and a second image sequence are acquired, and thus a first object and a second object are reconstructed and generated based on the first image sequence and the second image sequence respectively. The registration of the first object and the second object are further performed, and a mapping relationship obtained according to a registration result may indicate a correspondence between image frames in the first image sequence and image frames in the second image sequence. Compared with setting a difference value artificially, obtaining the correspondence between image frames in the first image sequence and image frames in the second image sequence by using the image matching method improves the matching accuracy.

Abstract: Disclosed is a method for training a neural network to quantify the vessel calibre of retina fundus images. The method involves receiving a plurality of fundus images; pre-processing the fundus images to normalise images features of the fundus images; and training a multi-layer neural network, the neural network comprising of a convolutional unit, multiple dense blocks alternating with transition units for down-sampling image features determined by the neural network, and a fully-connected unit, wherein each dense block comprises a series of cAdd units packed with multiple convolutions, and each transition layer comprises a convolution with pooling.

Abstract: A method for gating in tomographic imaging system includes steps of: (a) performing a tomographic imaging on an object with a target moving periodically along a first axis for acquiring projection images; (b) obtaining projected curves by summing up pixel values along a direction of a second axis perpendicular to the first axis in each projection image; (c) determining a target zone on the projection images, wherein a central position on the first axis of the target zone is corresponding to a position having the largest variation in the projected curves on the first axis; (d) calculating parameter values of pixel values in the target zones and obtaining a curve of a moving cycle of the target according to the parameter values; and (e) selecting the projection images under the same state in the moving cycle for image reconstruction according to the curve of the moving cycle of the target.

Abstract: A contrast element tracking method comprises obtaining a sequence of frames each comprising ultrasound or other medical imaging data representing an anatomical region of a human or animal subject at a respective different time; for each frame, identifying one or more portions of the ultrasound or other medical imaging data as single or multiple contrast element signal portions representative of a contrast element or plurality of contrast elements; assigning respective position data to each of the single contrast element signal portions and each of the multiple contrast element signal portions; and using a linking model that uses at least said assigned position data to link single or multiple contrast element signal portions represented in at least one of the frames to single or multiple contrast element signal portions represented in at least one other of the frames thereby to track movement of contrast elements through said region of the subject.

Abstract: Systems and methods are disclosed to objectively identify sub-second behavioral modules in the three-dimensional (3D) video data that represents the motion of a subject. Defining behavioral modules based upon structure in the 3D video data itself— rather than using a priori definitions for what should constitute a measurable unit of action— identifies a previously-unexplored sub-second regularity that defines a timescale upon which behavior is organized, yields important information about the components and structure of behavior, offers insight into the nature of behavioral change in the subject, and enables objective discovery of subtle alterations in patterned action. The systems and methods of the invention can be applied to drug or gene therapy classification, drug or gene therapy screening, disease study including early detection of the onset of a disease, toxicology research, side-effect study, learning and memory process study, anxiety study, and analysis in consumer behavior.

Abstract: The present disclosure relates to the field of artificial intelligence (AI) technologies, and provides an auxiliary photographing device for dyskinesia analysis, and a control method and apparatus for an auxiliary photographing device for dyskinesia analysis. The method includes controlling a camera assembly of the auxiliary photographing device at a first position to perform photographing, to obtain a first image, the first image comprising a target body part of a patient having dyskinesia; determining, in the first image, a position of a target region corresponding to the target body part; controlling an orientational movement of a mechanical arm of the auxiliary photographing device according to the position of the target region, to adjust the camera assembly to a second position; and controlling the camera assembly at the second position to perform photographing, to obtain a second image, the second image comprising the target body part.

Abstract: A method of determining a region of interest in an image of tissue of an individual by an apparatus including processing circuitry may include executing, by the processing circuitry, instructions that cause the apparatus to partition an image of tissue of an individual into a set of areas, identify a tissue type of each area of the image, and apply a classifier to the image to determine a region of interest, the classifier being configured to determine regions of interest based on the tissue types of the set of areas of the image.

Abstract: A video signal generating apparatus is disclosed which includes: a camera configured to generate a video signal; an operating device configured to operate at least either the camera or an apparatus configured to receive the video signal; a text data generating device configured to generate text data including a meaningful term in response to the operation performed on the operating device; and a text data inserting device configured to insert the text data generated by the text data generating device into the video signal in a corresponding manner.

Abstract: Systems, methods, and instrumentalities are described herein for constructing a multi-view patient model (e.g., a 3D human mesh model) based on multiple single-view models of the patient. Each of the single-view models may be generated based on images captured by a sensing device and, dependent on the field of the view of the sensing device, may depict some keypoints of the patient's body with a higher accuracy and other keypoints of the patient's body with a lower accuracy. The multi-view patient model may be constructed using respective portions of the single-view models that correspond to accurately depicted keypoints. This way, a comprehensive and accurate depiction of the patient's body shape and pose may be obtained via the multi-view model even if some keypoints of the patient's body are blocked from a specific sensing device.

Abstract: Systems and methods for visualizing an unstained sperm cell are presented, the system comprises a data input utility that receives measured data comprising at least one quantitative phase microscopy image of the unstained sperm cell; a data processing utility comprising an image analyzer module that utilizes characteristic refractive index information of one or more organelles of the sperm cell, to process the at least one quantitative phase microscopy image and generate at least one corresponding gradient image that includes edge enhancement of the one or more organelles, and a virtual staining module that applies one or more predetermined virtual staining functions to the at least one quantitative phase microscopy image and at least one corresponding gradient image, thereby virtually stain at least one of the one or more organelles of the sperm cell and generate virtually stained image data of the sperm cell; and an output utility that utilizes the virtually stained image data of the sperm cell and generate

Abstract: Systems, methods of and computer program products for predicting and detecting the onset of glaucoma are provided.

Abstract: A stroke detection system analyzes images of a person's face over time to detect asymmetric changes in the position of certain reference points that are consistent with sagging or drooping that may be symptomatic of a stroke or TIA. On detecting possible symptoms of a stroke or TIA, the system may alert caregivers or others, and log the event in a database. Identifying stroke symptoms automatically may enable more rapid intervention, and identifying TIA symptoms may enable diagnostic and preventative care to reduce the risk of a future stroke.

Abstract: A computer-implemented method that allows users evaluate the densities of images and search for abnormalities in three-dimensional space. The voxel buildup uses a series of two-dimensional images and evaluates every pixel based on the user described predetermined threshold value at runtime. A singular optimized voxel-generated mesh is spawned to represent the combined locations of every pixel.

Abstract: An apparatus for inspecting a target device includes a data communication interface and control circuitry configured to receive imaging data of a target device using the data communication interface, determine image features associated with the target device based at least in part on the imaging data, and determine an inspection outcome based at least in part on the image features.

Abstract: A method of processing a series of images of an embryo to determine estimated timings of developmental events for the embryo, wherein the method comprises: determining feature information for each image, the feature information for each image representing the content of the image; establishing machine learned classifiers for associating each image with a respective likelihood of the image being associated with one or more developmental events based on the feature information for the image; applying the machine learned classifiers to the feature information for each image to determine a respective likelihood of the image being associated with one or more developmental events, and determining estimated timings for the plurality of developmental events for the embryo from the respective likelihoods of the respective images being associated with respective ones of the plurality of developmental events. The method may further comprise determining an indication of a confidence estimate for the timings.

Abstract: A wrinkle detection method includes: rotating a region, in a face image, in which a wrinkle needs to be detected, to obtain a plurality of to-be-detected images; determining wrinkle points from all pixel points based on grayscale values of the pixel points in each of the to-be-detected images with different angles; determining at least one wrinkle line based on the wrinkle points; and then displaying, by the electronic device, the wrinkle line in the region in which the wrinkle needs to be detected, where each wrinkle line indicates one wrinkle in each of the to-be-detected images.

Abstract: A technology capable of estimating information on a position and a size of a pupil or an iris using an image obtained by photographing eyes of a subject even when a part of the pupil or the iris is hidden in the image is provided.

Abstract: Systems and methods are provided for training an artificial intelligence model for detecting calcified portions of a vessel in an input medical image. One or more first medical images of a vessel in a first modality and one or more second medical image of the vessel in a second modality are received. Calcified portions of the vessel are detected in the one or more first medical images, The artificial intelligence model is trained for detecting calcified portions of the vessel in the input medical image in the second modality based on the one or more second medical images and the detected calcified portions of the vessel detected in the one or more first medical images.

Abstract: Systems and methods facilitate privacy-preserving data curation in a federated learning system by transmitting a portion of a potential data sample to a remote location. The portion is inspected for quality to rule out data samples that do not satisfy data curation criteria. The remote examination focuses on checking the region of interest but maintains privacy as the examination is unable to parse any other identifiable subject information such as face, body shape etc. because pixels or voxels outside the portion are not included. The examination results are sent back to the collaborators so that inappropriate data samples can be excluded during federated learning rounds.

Abstract: A method for computing lung compliance imaging, the method comprising obtaining one or more images of lungs, determining a spatial transformation of each voxel within the lungs between the lungs at an inhale position and the lungs at an exhale position to provide displacement vector estimates for each voxel within the lungs, performing volume change inference operations to determine a volume change between the lungs at the inhale position and the lungs at the exhale position based on an inhale region of interest, an exhale region of interest, and the displacement vector estimates for each voxel within the lungs, computing a lung compliance based on the volume change inference operations.

Abstract: The invention provides for a medical apparatus (100, 400, 600) comprising a memory (110) for storing machine executable instructions (120) and a processor (104) for controlling the medical apparatus. Execution of the machine executable instructions causes the processor to: receive (200) a medical image (122) descriptive of a three-dimensional anatomy of a subject (418); and provide (202) an image segmentation (124) by segmenting the medical image into multiple tissue regions (300, 302) using a model-based segmentation. The model-based segmentation assigns a tissue type to each of the multiple regions. The model-based segmentation has a surface mesh (304). The segmentation is corrected by using the tissue type assigned to each of the multiple regions to correct for partial volume effects at boundaries formed by the surface mesh between at least some of the multiple tissue regions.

Abstract: Disclosed is an electronic device. The electronic device comprises: a first image sensor and a second image sensor; and a processor which alternately performs a first image capture mode, in which a plurality of captured images are acquired by controlling the respective exposure times of the first image sensor and the second image sensor differently, and a second imager capture mode, in which a plurality of captured images are acquired by controlling the respective exposure times of the first image sensor and the second image sensor identically, identifies an object by using the plurality of captured images acquired in the first image capture mode, and acquires distance information about the identified object on the basis of the plurality of captured images acquired in the second image capture mode.

Abstract: A body fluid analysis device includes processing circuitry. The processing circuitry is configured to set one or more subregions in a region of interest in a medical image. The processing circuitry is configured to set a reference direction for each of the subregions set. The processing circuitry is configured to determine a flow direction of a body fluid for each subregion. The processing circuitry is configured to determine the state of a flow of the body fluid in the region of interest on the basis of the reference direction for each subregion set and the flow direction of the body fluid for each subregion determined.

Abstract: A system and method for identifying abnormal medical images. The system can be configured to receive a medical image, segment an anatomical structure from the medical image to define a segmented dataset, register the segmented dataset to a baseline dataset defining a normal anatomical structure, classify, by an abnormality classifier, whether the anatomical structure within the medical image as either abnormal or normal, wherein the abnormality classifier comprises a machine learning algorithm trained to distinguish between normal and abnormal versions of the anatomical structure in medical images, and based on whether the anatomical structure can be segmented from the medical image, whether the segmented dataset can be registered to the baseline dataset, or a classification associated with the medical image output by the abnormality classifier, flagging the medical image as either normal or abnormal.

Abstract: Techniques are disclosed for detecting an uncovered portion of a body of a person in a frame of video content. In an example, a first machine learning model of a computing system may output a first score for the frame based on a map that identifies a region of the frame associated with an uncovered body part type. Depending on a value of the first score, a second machine learning model that includes a neural network architecture may further analyze the frame to output a second score. The first score and second score may be merged to produce a third score for the frame. A plurality of scores may be determined, respectively, for frames of the video content, and a maximum score may be selected. The video content may be selected for presentation on a display for further evaluation based on the maximum score.