Abstract: A processor divides a fundus region of an ultra-wide field fundus image into plural areas including at least a first area and a second area, generates first attribute information indicating an attribute of the first area and second attribute information indicating an attribute of the second area, and generates first mode instruction information to instruct display of the first area in a first mode corresponding to the first attribute information, and generates second mode instruction information to instruct display of the second area in a second mode corresponding to the second attribute information.

Abstract: Systems and methods of sensor data fusion including sensor data capture, curation, linking, fusion, inference, and validation. The systems and methods described herein reduce computational demand and processing time by curating data and calculating conditional entropy. The system is operable to fuse data from a plurality of sensor types. A computer processor optionally stores fused sensor data that the system validates above a mathematical threshold.

Abstract: A method for creating a camera model for a camera of a surgical microscope includes positioning a calibration object in an initial pose in an observation region of the camera, determining a pose delta for reaching a first pose for the calibration object in a measurement space of the camera starting from the initial pose, positioning the calibration object in the first pose in accordance with the determined pose delta, making a recording of the calibration object in the first pose with the camera, positioning the calibration object in at least one further pose, making a recording of the calibration object in the at least one further pose, and creating a camera model based on the recordings made, the first pose and the at least one further pose being chosen with a distribution in the measurement space such that a camera model is obtained which represents the entire measurement space.

Abstract: One or more example embodiments of the present invention relates in one aspect to a computer-implemented method includes receiving 2D topogram data of a patient; generating 2D topogram annotation data by applying a machine learning algorithm for topogram analysis onto the 2D topogram data; generating the medical imaging decision support data based on the 2D topogram annotation data; and providing the medical imaging decision support data.

Abstract: Systems, methods, and computer program products are provided for generating and improving multitask learning models. An example method includes determining a first accuracy metric based on at least two machine learning models performing a plurality of tasks, receiving a multitask learning model including at least one shared layer and a plurality of task-specific layers, determining a second accuracy metric based on the multitask learning model having a first number of shared layers, determining a third accuracy metric based on the multitask learning model having a second number of shared layers, comparing the accuracy metrics, repeating until at least one termination condition is satisfied, and determining a target number of shared layers for the multitask learning model based on at least one of the second accuracy metric, the third accuracy metric, the first number of shared layers, the second number of shared layers, or any combination thereof.

Abstract: Systems and methods of sensor data fusion including sensor data capture, curation, linking, fusion, inference, and validation. The systems and methods described herein reduce computational demand and processing time by curating data and calculating conditional entropy. The system is operable to fuse data from a plurality of sensor types. A computer processor optionally stores fused sensor data that the system validates above a mathematical threshold.

Abstract: Technology for guiding a user to collect clinically usable ultrasound images is described. In some embodiments, an ultrasound device may automatically change the elevational steering angle of its ultrasound beam (e.g., using beamforming) in order to collect ultrasound data from different imaging planes within the subject. A processing device in operative communication with the ultrasound device may select one of the collected ultrasound images based on its quality (e.g., select the ultrasound image having the highest quality), and then continue to collect ultrasound images using the elevational steering angle at which the selected ultrasound image was collected.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for adjusting a target neural network using automatically generated test cases before deployment of the target neural network in a deployment environment. One of the methods may include generating a plurality of test inputs by using a test case generation neural network; processing the plurality of test inputs using a target neural network to generate one or more test outputs for each test input; and identifying, from the one or more test outputs generated by the target neural network for each test input, failing test inputs that result in generation of test outputs by the target neural network that fail one or more criteria.

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: An image processing system accesses an image of a completed form document. The image of the form document includes one or more features, such as form text, at particular locations within the image. The image processing system accesses a template of the form document and computes a rotation and zoom of the image of the form document relative to the template of the form document based on the locations of the features within the image of the form document relative to the locations of the corresponding features within the template of the form document. The image processing system performs a rotation operation and a zoom operation on the image of the form document, and extracts data entered into fields of the modified image of the form document. The extracted data can be then accessed or stored for subsequent use.

Abstract: Various techniques are provided for training a neural network to classify images. A convolutional neural network (CNN) is trained using training dataset comprising a plurality of synthetic images. The CNN training process tracks image-related metrics and other informative metrics as the training dataset is processed. The trained inference CNN may then be tested using a validation dataset of real images to generate performance results (e.g., whether a training image was properly or improperly labeled by the trained inference CNN). In one or more embodiments, a training dataset and analysis engine extracts and analyzes the informative metrics and performance results, generates parameters for a modified training dataset to improve CNN performance, and generates corresponding instructions to a synthetic image generator to generate a new training dataset. The process repeats in an iterative fashion to build a final training dataset for use in training an inference CNN.

Abstract: Aspects presented herein may enable an LMF to configure AI/ML-based techniques/measurements for a set of base stations/TRPs to improve the performance of UL-based positioning. In one aspect, a network entity transmits a configuration to at least one network node to configure the at least one network node to perform an UL-based positioning measurement with at least one ML model, where each of the at least one ML model is associated with a corresponding ML model ID in which the at least one network node uses for the UL-based positioning measurement, where the UL-based positioning measurement is for a set of SRSs from a UE. The network entity receives the UL-based positioning measurement for the set of SRSs from the at least one network node. The network entity estimates a position of the UE based on the UL-based positioning measurement for the set of SRSs.

Abstract: A method for image generation based on a Generative AI Network. The Generative AI Network includes a generator and an encoder. The method includes determining, by the encoder, a first encoding E(Y) of a target image Y; generating, by the generator, a generated image G(Z) corresponding to the target image Y, wherein the generated image G(Z) is located in a close vicinity of a target neighborhood of the target image Y, and outputs of the generator are mapped, by the encoder, to a latent space adaptable to manipulate at least one characteristics of images generated by the Generative AI Network; and generating, by the encoder, a second encoding E(G(Z)) of the generated image G(Z) corresponding to the target image Y, wherein the first and second encodings E(Y) and E(G(Z)) map the target image Y and the generated image G(Z) to the latent space.

Abstract: Disclosed are a method, system, and apparatus of response plan modification through artificial intelligence applied to ambient data communicated to an incident commander. According to one embodiment, the method includes analyzing a description of a fire in progress, automatically generating an incident action plan through an Incident Action Artificial-Intelligence Model (“IAAIM”) based on the description of the fire in progress, and modifying the incident action plan based on a trusted radio communication to an incident commander.

Abstract: Systems and methods of sensor data fusion including sensor data capture, curation, linking, fusion, inference, and validation. The systems and methods described herein reduce computational demand and processing time by curating data and calculating conditional entropy. The system is operable to fuse data from a plurality of sensor types. A computer processor optionally stores fused sensor data that the system validates above a mathematical threshold.

Abstract: An apparatus (10) for manually auditing a set (30) of images having quality ratings (38) for an image quality metric assigned to the respective images of the set of images by an automatic quality assessment process (40) includes at least one electronic processor (20) programmed to: generate quality rating confidence values (42) indicative of confidence of the quality ratings for the respective images; select a subset (32) of the set of images for manual review based at least on the quality rating confidence values; and provide a user interface (UI) (27) via which only the subset of the set of images is presented and via which manual quality ratings (46) for the image quality metric are received for only the subset of the set of images.

Abstract: A display control apparatus including at least one processor is provided. The processor is configured to display at least one first region including at least one finding on at least one first slice image of a first three-dimensional medical image on a display and display at least one second region with a maximum size of finding on at least one second slice image of at least one second three-dimensional medical image on the display.

Abstract: A computer-implemented method and system are for parametrizing a function including a processing algorithm and a representation generator, the representation generator being designed to generate at least one representation. In an embodiment, the method includes using an optimization algorithm to determine the processing algorithm and the at least one representation parametrization. The optimization algorithm optimizes a measure for the performance of the processing algorithm when operating on a set of training representations generated by applying the representation generator to training medical image datasets, by varying on the one hand the content of the at least one representation parametrization and/or the number of used representation parametrizations and on the other hand the processing algorithm and the algorithm parameters.

Abstract: A method includes receiving from a camera a 2D front-view digital image (FDI) and side-view digital image (SDI) of a human body; receiving one or more camera parameters (CPs); executing a front depth-estimation model (DEM) generated through pre-training a first machine-learning model (MLM) to convert the FDI and SDI into a front depth map (DM) and side DM, respectively; executing a rear DEM generated through pre-training a second MLM to estimate a rear DM based on the FDI, SDI, and front and side DMs; combining the front and rear DMs to generate a 3D model; executing a front key-point (FKP) estimation model generated through pre-training a third MLM to estimate one or more FKPs; and extracting a body measurement based on the 3D model and FKPs, the first and second MLMs each including a respective encoder and decoder, each respective decoder configured to be executed based on the CPs.

Abstract: A trained first model is generated through first learning using a first learning image group constituted of a normal image which is a medical image having no region of interest. An input image group including at least the medical image different from the first learning image group is input to the trained first model, and abnormality detection is performed. The extracted image used for learning to prevent erroneous recognition is sorted according to a result of the abnormality detection, and second learning using a second learning image group including at least the extracted image is performed. A second model that detects the region of interest is generated through the second learning.