Abstract: A method, computer program, and computer system is provided for estimating three-dimensional hand poses in images. Data corresponding to two hand images is receive, and an optical flow value corresponding to a change in a hand gesture in the received hand image data is calculate. A heat map is generated based on the calculated optical flow, and a hand mesh map is estimated based on the generated heat map. A hand pose present within the hand images is determined based on the estimated hand mesh map.

Abstract: Embodiments of the present disclosure include a method, device and computer readable medium involving receiving image data of one or more coronary arteries, generating a binary segmentation indicating presence of calcium in the one or more coronary arteries from the image data, generating a branch density of the one or more coronary arteries, and assigning a coronary artery label from the branch density to the binary segmentation such that at least one indication of presence of calcium of the binary segmentation is labeled as present in a specific one of the one or more coronary arteries.

Abstract: A method and apparatus are provided that includes, in a same framework, storing an artificial intelligence (AI) model, loading the AI model into a serving platform, loading and testing a test unit against the AI model loaded into the serving platform, and collecting reports from results of storing the AI model, loading the AI model into the serving platform and testing the test unit.

Abstract: A computer-implemented method, computer readable storage medium, and computer system is provided for estimating three-dimensional (3D) hand poses in images by receiving data corresponding to a hand image, generating a depth map corresponding to the received hand image data, and estimating a hand pose from the received hand image data and the generated depth map.

Abstract: A method, computer program, and computer system is provided for receiving data corresponding to a tomograph scan associated with a patient, extracting slices from the received tomograph scan data, and determining adjacent slices for each of the extracted slices. The extracted slices and the adjacent slices may be grouped into slabs, and features associated with the slabs may be identified. It may be determined that a slab corresponding to the identified features contains a feature associated with ICH.

Abstract: Embodiments of the present disclosure include a method, device and computer readable medium involving receiving image data of one or more coronary arteries, generating a binary segmentation indicating presence of calcium in the one or more coronary arteries from the image data, generating a branch density of the one or more coronary arteries, and assigning a coronary artery label from the branch density to the binary segmentation such that at least one indication of presence of calcium of the binary segmentation is labeled as present in a specific one of the one or more coronary arteries.

Abstract: A method and apparatus are provided that includes, in a same framework, storing an artificial intelligence (AI) model, loading the AI model into a serving platform, loading and testing a test unit against the AI model loaded into the serving platform, and collecting reports from results of storing the AI model, loading the AI model into the serving platform and testing the test unit.

Abstract: There is included an apparatus and system including image segmentation code, configured to cause at least one hardware processor to segment an image of a person's hand from an input image, and classification code configured to cause the at least one processor to classify the segmented image of the person's hand according to at least one predefined pose.

Abstract: A method and apparatus include receiving a three dimensional (3D) non-contrast computed tomography (NCCT) image of a head including a hematoma. A plurality of two dimensional (2D) images of the head including the hematoma are generated using the 3D NCCT image of the head including the hematoma. A plurality of 2D hematoma images are generated using a first 2D convolutional neural network (CNN) based on the plurality of 2D images. A 3D region of interest (ROI) that encompasses the hematoma is identified based on the plurality of 2D hematoma images. A plurality of 2D images that correspond to the ROI are generated. A hematoma expansion (HE) prediction score is determined using a second CNN based on the plurality of 2D images that correspond to the ROI. The HE prediction score is provided.

Abstract: A method of medical data auto collection segmentation and analysis, includes collecting, from a plurality of sources, unstructured medical data in a plurality of formats, recognizing a medical name entity of each piece of the unstructured medical data, using a medical dictionary, and performing semantic text segmentation on each piece of the unstructured medical data so that each piece of the unstructured medical data is partitioned into groups sharing a same topic. The method further includes generating, as structured medical data, each piece of the unstructured medical data of which the medical name entity is recognized, each piece of the unstructured medical data being partitioned into the groups, and indexing the structured medical data into elastic search clusters.

Abstract: Provided are a method and an apparatus for receiving a query including a sequence of words. The sequence of words is converted into a sequence of feature vectors. A semantic meaning of the sequence of words is generated using a bi-directional long-short term memory (LSTM). The LSTM is regularized using a Gaussian mixed model (GMM) based on the generated semantic meaning of the sequence of feature vectors.

Abstract: A method and user device for determining a unified Parkinson's disease rating scale (UPDRS) value associated with a user of the user device include obtaining video data associated with a movement of a body part of the user. The UPDRS value is determined using a model and the video data associated with the movement of the body part of the user. The UPDRS value is provided to permit an evaluation of the user based on the UPDRS value.

Abstract: A method of synthesizing an image of a hand using a blending generative adversarial network (BlendGAN) includes obtaining a synthetic 3-dimensional (3D) hand pose including a 3D model of a hand; obtaining a real background image; combining the synthetic 3D hand pose with the real background image to create a synthetic hand image; and blending the synthetic hand image using the BlendGAN to create a blended synthetic hand image.

Abstract: A method and user device for providing a unified Parkinson's disease rating scale (UPDRS) value by a user device includes generating, by a sensor of the user device, sensor data based on a user of the user device manipulating the user device. The UPDRS value is determined based on the sensor data and a deep neural network (DNN) model. The UPDRS value is provided to permit an evaluation of the user based on the UPDRS value.

Abstract: A method and apparatus include receiving a first sentence including a first set of words, and a second sentence including a second set of words. A first set of vectors corresponding to the first set of words of the first sentence, and a second set of vectors corresponding to the second set of words of the second sentence are generated using a word embedding model. A similarity matrix based on the first set of vectors and the second set of vectors is generated. An alignment score associated with the first set of vectors and the second set of vectors is determined using the similarity matrix. The alignment score is transmitted to permit information retrieval based on a similarity between the first sentence and the second sentence.

Abstract: A method and apparatus for generating augmented training data for hand pose estimation include receiving source data that is associated with a first lighting condition. Target data that is associated with a second lighting condition is received. A lighting condition translation between the first lighting condition and the second lighting condition is determined. Lighting translated data is generated based on the lighting condition translation and the source data. Augmented training data for hand pose estimation is generated based on the target data and the lighting translated data.

Abstract: Embodiments of the present disclosure include a method, device and computer readable medium involving receiving image data of one or more coronary arteries, generating a binary segmentation indicating presence of calcium in the one or more coronary arteries from the image data, generating a branch density of the one or more coronary arteries, and assigning a coronary artery label from the branch density to the binary segmentation such that at least one indication of presence of calcium of the binary segmentation is labeled as present in a specific one of the one or more coronary arteries.

Abstract: A method and apparatus include receiving, by a device, medical information associated with a user. Inquiry information is determined based on the medical information associated with the user and a reinforcement learning model. The inquiry information is provided to permit response information to be received. The response information is received based on providing the inquiry information. Diagnosis information is determined based on the medical information and the response information using a machine learning model. The diagnosis information is provided to a set of devices via a network.

Abstract: A method for processing unstructured Chinese-language medical text includes identifying a medical entity in the unstructured Chinese-language medical text using an attention-based named-entity recognition (NER) model, structuring the identified medical entity using a multiple-dimensional entity understanding framework, normalizing the structured medical entity using a medical knowledge graph, and outputting the normalized medical entity.

Abstract: A method of medical data auto collection segmentation and analysis, includes collecting, from a plurality of sources, unstructured medical data in a plurality of formats, recognizing a medical name entity of each piece of the unstructured medical data, using a medical dictionary, and performing semantic text segmentation on each piece of the unstructured medical data so that each piece of the unstructured medical data is partitioned into groups sharing a same topic. The method further includes generating, as structured medical data, each piece of the unstructured medical data of which the medical name entity is recognized, each piece of the unstructured medical data being partitioned into the groups, and indexing the structured medical data into elastic search clusters.