Tencent America LLC

Microsoft Technology Licensing, LLC

Min Tu

Wei Fan

Shangqing Zhang

Tao Yang

Kun Wang

Yusheng Xie

Nan Du

Lianyi Han

Hui Tang

Yaliang Li

Xu Wang

Xiaozhong Chen

Zeyu You

Chao Huang

Zhen Qian

Kapil Laxmikant Surlaker

Lin Qiao

Shih-Yao Lin

Shirshanka Das

Yinan Li

Chavdar Botev

Issac Buenrostro

Sahil Takiar

Ziyang Liu

Narasimha R Veeramreddy

Ying Dai

Kenneth D Goodhope

A method, computer program, and computer system is provided for query matching of sentences based on co-attention scores. Two or more query inputs to a neural network are received. A correlation factor between the two or more query input is identified based on attention weights. A feature vector is generated based on the attention weights. A probability value corresponding to the two or more query inputs is determined based on the generated feature vector.

Efficient and compact text matching system for sentence pairs

A method and apparatus for performing a biosignal analysis task using a set of models includes receiving an input biosignal. Information that identifies the biosignal analysis task to be performed in association with the input biosignal is received. A waveform model and a digital signal processing (DSP) model are selected. A first type of feature and a second type of feature of the input biosignal are identified. An analysis model is selected, and the biosignal analysis task is performed using the analysis model.

Digital signal processing assistant modeling method for biosignal analysis

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.

System and method for clinical decision support system with inquiry based on reinforcement learning

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.

Machine learning model full life cycle management framework

A method and device for generating a three dimensional (3D) bounding box of a region of interest (ROI) of a patient include receiving a two dimensional (2D) maximum intensity projection (MIP) image that is an axial view of the patient and a 2D MIP image that is a sagittal view of the patient. A first 2D bounding box of the ROI of the patient and a second 2D bounding box of the ROI of the patient are detected using the 2D MIP images. A 3D MIP image of the patient is received, and the 3D bounding box of the ROI of the patient is generated using the 3D MIP image, the first 2D bounding box, and the second 2D bounding box. The 3D MIP image including the 3D bounding box is provided.

System and method for identifying target regions prior to organs at risk segmentation

A method, computer program, and computer system for detecting and classifying atrial fibrillation by receiving data corresponding to an electrocardiogram (ECG) associated with a patient, extracting RR intervals from the received ECG data, determining previous RR intervals for each of the extracted RR intervals and aggregating features associated with the RR intervals and the previous RR intervals. Patterns associated with the aggregated features are classified, and the computer may determine that a sample of the ECG data corresponding to one or more of the classified patterns contains a pattern associated with atrial fibrillation.

Deep neural network on ECG Poincare plot for atrial fibrillation classification

A method and device for performing electrocardiography (ECG) analysis, the method including receiving ECG data that is from one or more leads, generating an image based on the ECG data, obtaining a feature map based on the image, inputting the feature map to a first neural network, the first neural network configured to generate an output based on the feature map inputted, inputting the output of the first neural network to a second neural network, the second neural network configured to obtain at least one temporal feature of the image based on the output of the first neural network and a previous state of the second neural network, and classifying a signal included in the ECG data based on the at least one temporal feature obtained by the second neural network.

Framework for performing electrocardiography analysis

A method, computer program, and computer system is provided for text error identification and correction. A text input having a phonetic component and a glyphic component is received. Information corresponding to the phonetic component and the glyphic component is coded as a fixed-length sequence. One or more candidate replacement words corresponding to the fixed-length sequence are identified. At least a portion of the text input is replaced with a candidate replacement word from among the one or more candidate replacement words.

Framework for chinese text error identification and correction

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.

Understanding a query intention for medical artificial intelligence systems using semi-supervised deep learning

A method of performing electrocardiography (ECG) analysis by at least one processor, the method including receiving ECG data that is from multiple leads; grouping the ECG data into groups of data; generating, from each group of the groups of data, a feature vector using a respective machine learning model; and performing ECG analysis using the feature vectors generated from each of the groups of data.

Training framework for multi-group electrocardiography (MG-ECG) analysis

A method and apparatus are provided that includes iteratively sampling candidates from medical records and evaluating whether ones of the candidates better explain a member from the medical records. The iterations replace the member with the candidates and depending on whether the candidates better explain the member from the medical records may be weighted in a next iteration.

Method for determining disease symptom relations using acceptance and rejection of random samples

There is included an apparatus and system including an intra-heartbeat (HB) extraction code configured to extract intra-HB features from electrocardiography (ECG) signals, and an inter-HB extraction code configured to extract inter-HB features from the ECG signals, and at least one attention mechanism code configured to control at least one of the intra-HB extraction code and inter-HB extraction code based on at least one attention mechanism.

Explainable artificial intelligence framework for electrocardiography analysis

A method of determining a risk probability of vertebral artery dissection (VAD) in a patient, including receiving medical image information of the patient and clinical report information of the patient; extracting at least one biomarker corresponding to a vertebral artery segment included in the medical image information; extracting patient history information from the clinical report information; and determining the risk probability of VAD using a deep learning classification model based on the extracted at least one biomarker and the extracted patient history information.

Growing community of inventors

Cupertino, CA, United States of America

Min Tu