Abstract: A system, method, and computer program product for registering two or more patient images for change assessment over time. An example aspect is configured to: obtain a new image of an area with an image capture system; obtain a reference image of a similar area; perform pre-processing of the new image and the reference image; perform a coarse alignment of the new image and the reference image; perform a high-resolution estimate; perform a high-resolution alignment; cross-check the at least one-point match to eliminate false matches and confirm correct matches of the high-resolution new image and the high-resolution reference image; perform segmentation of the high-resolution new image and the high-resolution reference image; perform analysis on at least one lesion in the high-resolution new image and the high-resolution reference image; and display a result of the analysis on a validator.

Abstract: In various embodiments, image sensors are configured for detecting object distance based on images captured by the image sensors. In those embodiments, parameters within the images are analyzed to determine a distance of the object relative to the image sensors. In some implementations, techniques for distance detecting object distance in accordance with the present disclosure are deployed within a vehicle. In those implementations, the distance sensing in accordance with the present disclosure can be used to aid various driving scenario, such as different levels of autonomous self-driving by the vehicle. In some implementations, the distance sensing can be employed in robotic equipment such as unmanned underwater devices to aid distance sensing of certain underwater objects of interest. In some implementations, the distance sensing can be employed in monitoring or surveillance for detecting or measuring object distance relative to a reference point.

Abstract: An AI-based system and method for supporting differential diagnosis and standard of care in healthcare. The method involves receiving patient information from various sources, including patient-reported symptoms, physician notes, and sensor data from medical devices. The patient information is preprocessed and analyzed using deep learning models to generate a ranked list of potential diagnoses, each associated with likelihood scores and key contributing factors. The potential diagnoses are provided to physicians via an interactive interface, and physician feedback is collected to fine-tune the AI models using reinforcement learning. The method aims to enhance physician decision-making, improve diagnostic efficiency, and ensure adherence to the standard of care by leveraging AI's ability to analyze vast amounts of data more effectively than human physicians.

Abstract: The present invention relates to biometric identification using a combination of static pattern characteristic unique to an individual and a measure of a dynamically changing blood flow characteristic for the individual. Images are acquired of the microvasculature of the outer eye (e.g. the sclera) which presents a unique pattern for each individual which can be determined using image processing and artificial intelligence (AI) techniques. A series of images are acquired of the microvasculature of the outer eye (e.g. the sclera) at a higher magnification thereby allowing for the determination of blood flow (e.g. velocity) characteristics using computer vision and AI techniques. The pattern and blood flow characteristics are used in combination to determine the identity of the individual.

Abstract: A medical image processing method for processing a pediatric simple X-ray image using a machine learning model and a medical image processing apparatus therefor are provided. The apparatus applies a style conversion model to a CT image pair including a basic CT image and a suppression CT image where at least a portion of a bone of the basic CT image is suppressed to convert the CT image pair into a conversion image pair and trains a bone suppression model for a simple X-ray image based on training data including the conversion image pair.

Abstract: According to one embodiment, a data processing device includes an acquisition part, and a processor. The acquisition part is configured to acquire first data including time-series image data. The processor is configured to derive first feature information based on a multidimensional array of n dimensions based on the first data acquired by the acquisition part. n is an integer not less than 3. A first axis of the multidimensional array is related to time.

Abstract: The present disclosure provides a privacy control circuit including an array of pixel cells having a first output data path and a second output data path, the first output data path including a one-time data protection circuitry, a sensor communication interface communicatively coupled to the first output data path, an on-sensor processor coupled to the second output data path and communicatively attached to the sensor communication interface, and a data register communicatively attached to the sensor communication interface.

Abstract: Provided is a method for computing a SYNTAX score using a cardio angiogram, which is performed by at least one processor of a computing device, and includes acquiring an angiogram of a cardiovascular system, providing a cardiovascular segment map associated with the angiogram, in response to a user input that selects one of one or more frames included in the acquired angiogram and associates the selected one frame with a cardiovascular segment included in the cardiovascular segment map, associating the selected one frame with the cardiovascular segment, generating, using the selected one frame, an analysis result for a lesion in the associated cardiovascular segment, determining, based on the analysis result, a SYNTAX score for at least a part of the cardiovascular system, and generating an indication of the SYNTAX score.

Abstract: A method and apparatus for object tracking are provided, where the object tracking method includes determining box information of candidate boxes in a current image frame and similarity scores of the candidate boxes based on including a search region of the current image frame with a template image corresponding to a target object, adjusting the similarity scores of the candidate boxes using a distractor map including distractor information of a previous image frame, determining a target box corresponding to the target object and a distractor box corresponding to a distractor of the target object from the candidate boxes based on the adjusted similarity scores, and updating the distractor map based on distractor information of the current image frame according to the distractor box.

Abstract: Systems and methods for updating a predicted outcome during a surgical procedure are disclosed. The system may include at least one processor configured to perform operations that include receiving, from at least one image sensor, image data associated with a first event and image data associated with a second event during a surgical procedure. Operations may include determining, based on received image data associated with the first event, a predicted outcome associated with the surgical procedure. Operations may include determining, based on the received image data associated with the second event, a change in the predicted outcome, causing the predicted outcome to drop below a threshold. Operations may include accessing a data structure of image-related data based on prior surgical procedures, identifying, based on the data structure, a recommended remedial action, and outputting the recommended remedial action.

Abstract: Systems and methods of facilitating determination of risk of coronary artery disease (CAD) based at least in part on one or more measurements derived from non-invasive medical image analysis. The methods can include accessing a non-invasive generated medical image, identifying one or more arteries, identifying, regions of plaque within an artery, analyzing the regions of plaque to identify low density non-calcified plaque, non-calcified plaque, or calcified plaque based at least in part on density, determining a distance from identified regions of low density non-calcified plaque to one or more of a lumen wall or vessel wall, determining embeddedness of the regions of low density non-calcified plaque by one or more of non-calcified plaque or calcified plaque, determining a shape of the more regions of low density non-calcified plaque, and generating a display of the analysis to facilitate determination of one or more of a risk of CAD of the subject.

Abstract: The present invention is directed to a method for the prediction of coke morphology from feed characteristics using cross-polarized light optical microscopy, image segmentation, and statistical analysis.

Abstract: An AI-based system and method for providing warning of potential health concerns. The invention involves receiving patient information from various sources, including one or more of sensor data, patient-reported symptoms, and medical records. The patient information is processed using AI models to identify potential health concerns. The AI models may identify user-specific patterns and/or metrics associated with potential health concerns. Tiered alerts may be generated and provided to a user based on the AI analysis. Recommended actions may be generated and provided to the user based on the alert.

Abstract: Systems and methods are provided for a deep learning-based digital breast tomosynthesis (DBT) image reconstruction that mitigates limited angular artifacts and improves in-depth resolution of the resulting images. The systems and methods may reduce the sparse-view artifacts in DBT via deep learning without losing image sharpness and contrast. A deep neural network may be trained in a way to reduce training-time computational cost. An ROI loss method may be used for further improvement on the resolution and contrast of the images.

Abstract: The present disclosure provides methods, apparatuses, and computer-readable mediums for image processing. In some embodiments, a method of image processing includes acquiring, from a user, a first image. The method further includes removing, using an image de-filter network, a filter effect applied to the first image to generate a second image. The method further includes obtaining, based on the first image and the second image, an image filter corresponding to the filter effect. The method further includes rendering a third image using the obtained image filter to output a fourth image.

Abstract: A handheld medical diagnostic device integrates at least seven sensor modules, including a high-magnification camera, otoscope camera, stethoscope, infrared thermometer, EKG, pulse oximeter, body composition monitor, glucometer, and/or hematology analyzer. The device features a system-on-chip (SoC) processor for intelligent data management, edge computing, and cloud-based AI processing, while applying privacy-preserving techniques. A wireless transceiver enables data transmission and reception between the sensors, edge compute nodes, and cloud platforms. The ergonomically designed housing includes a display with a force-sensitive layer for user input and navigation. The high-magnification camera module offers 300× magnification for visualizing blood cells and skin, with an annular LED array, encryption engine, and physically unclonable function (PUF) circuit. The otoscope camera module features a narrow profile for ear, nose, and throat imaging, with an annular LED array.

Abstract: A biometric sensor may include a scanner configured to capture a biometric data and an adjustment mechanism configured to respond to a force applied to the biometric sensor by shifting the biometric sensor from a neutral position to an adjusted position. The adjustment mechanism may be configured to respond to the removal of the force by returning the biometric sensor to the neutral position. While the biometric sensor is in the neutral position, the scanner may be capable of capturing a biometric data of a majority of users interacting with the apparatus. Accordingly, the biometric sensor may be able to operate with minimal adjustments. The biometric sensor may be part of a dispensing cabinet such that the biometric data captured by the biometric sensor may be used to control access to the dispensing cabinet. Related methods are also disclosed.

Abstract: Systems and methods for image processing are provided in the present disclosure. The systems may generate a preliminary image by filtering image data generated by an image acquisition device. The system may generate an intermediate image by performing, based on a first objective function, a first iterative operation on the preliminary image. The first objective function may include a first term associated with a first difference between the intermediate image and the preliminary image, a second term associated with continuity of the intermediate image and a third term associated with sparsity of the intermediate image. The systems may also generate a target image by performing, based on a second objective function, a second iterative operation on the intermediate image. The second objective function may be associated with a system matrix of the image acquisition device and a second difference between the intermediate image and the target image.

Abstract: This invention presents a multisensor-connected, AI-enabled telehealth system for assisting healthcare providers with differential diagnosis and patients with early health concern detection. The system comprises a multi-sensor medical device with at least seven sensors, a secure cloud-based platform, and an interactive telehealth module. The device preprocesses and securely transmits patient information to the cloud platform, where an ensemble of deep learning models analyzes the data to generate ranked potential diagnoses with likelihood scores. The telehealth module facilitates communication between providers, patients, and the cloud platform, presenting visualizations and receiving feedback. The system continuously updates and fine-tunes its models using incremental learning algorithms, adapting to new data while retaining previous knowledge. It also generates alerts for providers and patients when deviations from normal physiological patterns are detected, accompanied by explainable AI visualizations.

Abstract: A computer system implements a neural network to process raw dental images to detect and number teeth and to diagnose pathological, non-pathological, and post-treatment conditions. Detected teeth, corresponding numbers, and any corresponding detected conditions are correlated to the dental image and presented in a graphical user interface comprising the image and a standard, symbolic dental chart associating the tooth number, detected conditions, and regions of the image to teeth represented in the symbolic chart.