Abstract: Embodiments of the disclosure include methods for implementing a predictive model that predicts pluripotency of cells through a cost efficient and non-destructive means. The predictive model analyzes contrast images captured from the cells and outputs predictions of cellular pluripotency at the cellular level. Thus, implementation of the predictive model guides the selection and isolation of cells that are predicted to be pluripotent. Furthermore, the predictive model facilitates retrospective analyses to correlate pluripotency metrics with differentiation success and further enables tracking of cellular pluripotency over time (e.g., to evaluate differentiation of cells).

Abstract: A method and an apparatus for determining a three-dimensional directedness-determined motion are provided, including a forward-backward directedness, characterizing the motion of a movable ultrasound probe (10) during acquisition of an ultrasound image of a volume portion (2) by the ultrasound probe. The method comprises determining, by a machine-learning module (50), a motion indicator (60) indicating a three-dimensional motion between the ultrasound image frames (22); and determining, by a directedness-determining system (56), a directedness indicator (66) of the three-dimensional motion between the ultrasound image frames (22). The method further comprises determining a directedness-determined motion indicator (96) indicating the three-dimensional directedness-determined motion, including a determined the forward-backward directedness of the motion, between the ultrasound image frames (22) from the motion indicator (60) and the directedness indicator (66).

Abstract: An estimation apparatus includes an input unit and an approximator. Input information including an image in which a bone appears is input into the input unit. The approximator is configured to determine an estimation result related to bone density of the bone from the input information. The approximator includes a learned parameter to obtain the estimation result.

Abstract: According to an embodiment, a system comprises a communication module providing a communication interface, a camouflage pattern evaluation module performing an artificial intelligence-based camouflage pattern evaluation algorithm on an operation environment image and a camouflage pattern image, analyzing a similarity between the operation environment image and the camouflage pattern image, and obtaining an evaluation result of camouflage performance for the camouflage pattern in the operation environment, and a processor deriving a quantitative camouflage performance value for the evaluation result. The artificial intelligence-based camouflage performance evaluation algorithm extracts feature information for the operation environment image and the camouflage pattern image and analyzes the similarity in color, pattern, or structure between the operation environment image and the camouflage pattern image based on the extracted feature information.

Abstract: The invention relates to a non-invasive process for evaluating the quality of one or more dense connective tissue(s) in a patient, comprising the following steps: a) Analyzing the profile of the microrelief of a cutaneous replica of a portion of the skin of said patient by at least one of the following step: a1. visually assessing on picture(s) of said cutaneous replica the line shape and the anisotropy of the lines; and/or a2. Determining, on picture(s) of said cutaneous replica, the roughness index of the microrelief with an optical sensor, b) identifying cutaneous replica of “stage 1”, representative of healthy skins, and cutaneous replica of “stage 2” representative of altered skins, a cutaneous replica of stage 2 being indicative of low quality of the one or more dense connective tissue(s) in the patients body.

Abstract: A system for determining whether a dataset including a plurality of cross-sectional images includes a predetermined feature is provided. A first AI receives a dataset including a plurality of cross-sectional images, and analyses the dataset to identify a subset of cross-sectional images of the dataset capable of including the predetermined feature A second AI model receives a first cross-sectional image from the subset, analyses the first cross-sectional image to determine whether the first cross-sectional image includes the predetermined feature, and outputs an indication of whether the first cross-sectional image includes the predetermined feature. A processor is configured to obtain the output from the second AI model, and based on the output from the second AI model indicating that the first cross-sectional image includes the pre-determined feature, determine that the dataset includes the predetermined feature.

Abstract: The present disclosure relates to a discovery platform including machine-learning techniques for using medical imaging data to study a phenotype of interest, such as complex diseases with weak or unknown genetic drivers. An exemplary method of identifying a covariant of interest with respect to a phenotype comprises: receiving covariant information of a covariate class and corresponding phenotypic image data related to the phenotype obtained from a group of clinical subjects; inputting the phenotypic image data into a trained unsupervised machine-learning model to obtain a plurality of embeddings in a latent space, each embedding corresponding to a phenotypic state reflected in the phenotypic image data; and determining, based on the covariant information for the group of clinical subjects, the plurality of embeddings, and one or more linear regression models, an association between each candidate covariant of a plurality of candidate covariants and the phenotype state to identify the covariant of interest.

Abstract: The present invention discloses the cross-domain network method for magnetic resonance imaging undersampling trajectory optimization in Fourier domain and reconstruction network in image domain. The method includes the following steps: obtaining a head MR image, preprocessing, and obtaining simulated fully sampled k-space data through Fourier Transform; separating the real and imaginary parts of the simulated fully sampled k-space data and independently storing them in two matrices with the same dimensions, then merging them into two channels as inputs to the cross-domain network; constructing the cross-domain network, including the undersampling layer, the Inverse Fourier Transform layer, and the reconstruction network; training the cross-domain network until convergence; using the trained network to acquire and reconstruct the head MR image.

Abstract: A monitoring system is configured to monitor a property. The monitoring system includes a camera, a sensor, and a monitor control unit. The monitor control unit is configured to receive image data and sensor data. The monitor control unit is configured to determine that the image data includes a representation of a person. The monitor control unit is configured to determine an orientation of a representation of a head of the person. The monitor control unit is configured to determine that the representation of the head of the person likely includes a representation of a face of the person. The monitor control unit is configured to determine that the face of the person is likely concealed. The monitor control unit is configured to determine a malicious intent score that reflects a likelihood that the person has a malicious intent. The monitor control unit is configured to perform an action.

Abstract: The present disclosure relates generally to an autonomous cell imaging and modeling platform, and more specifically to machine-learning techniques for using microscopy imaging data to continuously study live biological cells. The autonomous cell imaging and modeling platform can be applied to evaluate various cellular processes, such as cellular differentiation, optimization of cell culture (e.g., in-plate cytometry), disease modeling, histopathology imaging, and genetic and chemical screening, using a dynamic universal imaging system. In some embodiments, the platform comprises a set of label-free computational imaging techniques, self-supervised learning models, and robotic devices configured in an autonomous imaging system to study positional and morphological characteristics in particular cellular substructures of a cell culture in an efficient and non-destructive manner over time.

Abstract: A method for training an algorithm for predicting a knee adduction moment (KAM) includes, while each subject walks over forceplates, capturing kinematic data, generating first ground reaction force (GRF) data, generating second GRF data, and generating reference KAM data based on the kinematic data and the first GRF data. While repeatedly training the algorithm by incrementing i by one, the method performs generating a model, which predicts reference KAM data, validating the predicted reference KAM data based on reference KAM data of the subjects other than the i-th subject, adjusting internal parameters by minimizing an error between the predicted KAM data and reference KAM data of the subjects other than the i-th subject, and producing an accuracy score for the model based on an error between the predicted reference KAM data and the reference KAM data of the i-th subject.

Abstract: A method of processing magnetic resonance data of a sample under investigation includes the steps of provision of the MR data being collected with an MRI scanner apparatus, and machine learning based data analysis of the MR data by supplying the MR data to an artificial neural network being trained with predetermined training data, wherein at least one image parameter of the sample and additionally at least one uncertainty quantification measure representing a prediction error of the at least one image parameter are provided by output elements of the neural network. Furthermore, a magnetic resonance imaging (MRI) scanner apparatus being adapted for employing the method of processing MR data is described.

Abstract: A neural-network-based-implemented ophthalmologic intelligent consultation method includes: performing correction filtering on a consultation voice of a patient, framing the voice into a consultation voice frame sequence, generating a consultation text corresponding to the consultation voice frame sequence based on phoneme recognition and phoneme transcoding, and extracting an ophthalmologically-described disease; performing gray-level filtering, primary picture segmentation, and size equalization operation on an eye picture set of the to-be-diagnosed patient to acquire a standard eyeball picture group; extracting eye white features, pupil features and blood vessel features from the standard eyeball picture group, performing lesion feature analysis on the eye white features, the pupil features and the blood vessel features to acquire an ophthalmologically-observed disease, and based on the ophthalmologically-observed disease and the ophthalmologically-described disease, generating a consultation result.

Abstract: A method for detection and pathological classification of polyps via colonoscopy based on an anchor-free technique includes: performing feature extraction on a color endoscopic image that is pretreated, enhancing and extending the extracted features, decoding the feature information of the enhanced feature and the extended feature through an anchor-free detection algorithm to acquire a polyp prediction box and a prospect prediction mask, then respectively extracting global and local feature vectors from the extended feature and the prospect prediction mask, and combining the global feature vector with the local feature vector, so as to predict the type of polyps through a full-connection layer. Through the present application, the type of polyps can be correctly predicted, and the detection rate of polyps and the accuracy rate of pathological classification are improved.

Abstract: Techniques for processing multiplexed immunofluorescence (MxIF) images. The techniques include obtaining at least one MxIF image of a same tissue sample, obtaining information indicative of locations of cells in the at least one MxIF image, identifying multiple groups of cells in the at least one MxIF image at least in part by determining feature values for at least some of the cells using the at least one MxIF image and the information indicative of locations of the at least some cells in the at least one MxIF image and grouping the at least some of the cells into the multiple groups using the determined feature values, and determining at least one characteristic of the tissue sample using the multiple cell groups.

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: The present disclosure provides a method, device and equipment for identifying and detecting a macular region in a fundus image. The method includes the following steps: reading a current fundus image to be positioned and detected; detecting a macular region in the fundus image using a target detection model; when the macular region in the fundus image is not detected, detecting an optic disk region in the fundus image, and identifying and positioning the macular region based on the detected optic disk region; based on a positioning result of the macular region, extracting a macular image corresponding to the macular region from the fundus image; and performing multi-modal processing on the macular image, fusing images obtained by the multi-modal processing to obtain a fused image, and detecting whether the macular region is qualified or not according to the fused image.

Abstract: Surveillance systems process video streams obtained by a surveillance device, such as a drone, to either obscure or highlight objects in a surveillance area based on tags associated with the objects. A method of providing obscurant data includes receiving image data including an image of a target and receiving a preference setting corresponding to the target. Obscurant data of at least a portion of the image data corresponding to the target are determined using the received preference setting. A method of providing surveillance image data includes capturing image data including an image of a target, querying a database to receive a preference setting corresponding to the target, determining the obscurant data of the portion of the image data, and selectively modifying the received image data according to the determined obscurant data to provide the surveillance image data.

Abstract: A method including correcting output of an image sensor unit based on correction information of the image sensor unit that captures and discriminates a paper sheet. A apparatus includes an image sensor unit which includes an image capturing element that captures a banknote so as to discriminate the banknote, a controller that controls the image sensor unit, and a first attachment part, to which the image sensor unit is attached to be detachable, and which includes a connection terminal that connects the image sensor unit and the controller with each other, and which is arranged in a conveyance path for conveying the banknote.

Abstract: The present embodiments relate generally to a probe, system, and method for generating a predictive model for moving the probe. The probe can include a movable element that move according to the suggestion of the predictive model. The system can include the probe, a user device, an administrator processor, and a server. The predictive model calculates an image score based on the quality, then the processor can move the movable element based on the score.