公开(公告)号：US20240185575A1

公开(公告)日：2024-06-06

申请号：US18061024

申请日：2022-12-02

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Simona Rabinovici-Cohen ,  Ella Barkan ,  Tal Tlusty Shapiro

IPC: G06V10/774 ,  G06N3/0464 ,  G06V10/40 ,  G06V10/762 ,  G06V10/771 ,  G06V10/776 ,  G06V10/82

CPC classification number: G06V10/774 ,  G06N3/0464 ,  G06V10/40 ,  G06V10/762 ,  G06V10/771 ,  G06V10/776 ,  G06V10/82 ,  G06V2201/03

Abstract: An embodiment for generating balanced train-test splits for machine learning analysis. The embodiment may automatically extract low-level features and high-level features from a series of received datasets. The embodiment may automatically determine a series of impactful features for each of the received datasets correlating to a corresponding label. The embodiment may automatically select subsets of impactful features The embodiment may automatically cluster the received datasets to generate series of clusters, each of the generated series of clusters corresponding to one of the selected subsets of impactful features. The embodiment may automatically generate train-test split versions using datasets from each cluster in each of the generated series of clusters. The embodiment may automatically score each of the generated train-test split versions and select a highest-scoring train-test split version.

公开(公告)号：US20240184854A1

公开(公告)日：2024-06-06

申请号：US18438595

申请日：2024-02-12

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： Hong SHANG ,  Han ZHENG ,  Zhongqian SUN

IPC: G06F18/214 ,  G06F18/21 ,  G06N7/01 ,  G16H30/40 ,  G16H50/20

CPC classification number: G06F18/2155 ,  G06F18/217 ,  G06N7/01 ,  G16H30/40 ,  G16H50/20 ,  G06V2201/03

Abstract: A method for training an image recognition model includes: obtaining training image sets; obtaining a first predicted probability, a second predicted probability, a third predicted probability, and a fourth predicted probability based on the training image sets by using an initial image recognition model; determining a target loss function according to the first predicted probability, the second predicted probability, the third predicted probability, and the fourth predicted probability; and training the initial image recognition model based on the target loss function, to obtain an image recognition model.

公开(公告)号：US20240180404A1

公开(公告)日：2024-06-06

申请号：US18421613

申请日：2024-01-24

Applicant: Intuitive Surgical Operations, Inc.

Inventor： Ian E. McDowall ,  Jeffrey M. DiCarlo ,  Brian D. Hoffman ,  William Jason Culman

IPC: A61B1/00 ,  A61B1/04 ,  A61B1/06 ,  A61B5/00 ,  A61B34/00 ,  A61B34/20 ,  A61B34/30 ,  A61B34/35 ,  A61B90/00 ,  A61B90/30 ,  G02B27/10 ,  G06V20/20

CPC classification number: A61B1/00193 ,  A61B1/0005 ,  A61B1/00186 ,  A61B1/04 ,  A61B1/042 ,  A61B1/043 ,  A61B1/0638 ,  A61B5/0075 ,  A61B34/00 ,  A61B34/20 ,  A61B34/35 ,  A61B90/30 ,  A61B90/361 ,  G02B27/1006 ,  G06V20/20 ,  A61B2034/301 ,  A61B2090/371 ,  G06V2201/03

Abstract: In some embodiments, a controller of a computer-assisted surgical system receives a visible image captured by an image capture unit of a surgical system, receives a plurality of hyperspectral images captured at a same waveband by the image capture unit of the surgical system, generates a composite hyperspectral image from the plurality of hyperspectral images, and spatially registering the composite hyperspectral image with the visible image.

公开(公告)号：US12002211B2

公开(公告)日：2024-06-04

申请号：US18211819

申请日：2023-06-20

Applicant: Gauss Surgical Inc.

Inventor： Siddarth Satish ,  Kevin Miller

IPC: G06T7/00 ,  G01F1/00 ,  G01F1/661 ,  G06F18/24 ,  G06T7/62 ,  G06V10/764

CPC classification number: G06T7/0016 ,  G06F18/24 ,  G06T7/62 ,  G06V10/764 ,  G01F1/00 ,  G01F1/661 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/30024 ,  G06T2207/30104 ,  G06V2201/03

Abstract: Methods for characterizing fluids from a patient. A time series of images of a conduit are received, and a conduit image region in the images is identified. A flow type of the fluids passing through the conduit may be classified as one of air, laminar liquid, and turbulent liquid by evaluating an air-liquid boundary of the fluid. A volumetric flow rate of the fluids in the conduit is estimated. The volumetric flow rate may be based on the classified flow type. A concentration of a blood component of the fluids passing through the conduit may be estimated based on the images. A proportion of the fluid that is blood may also be determined, and a volume of blood that has passed through the conduit within a predetermined period of time may be estimated based on the estimated total volumetric flow rate and the determined proportion.

公开(公告)号：US20240161490A1

公开(公告)日：2024-05-16

申请号：US18504075

申请日：2023-11-07

Applicant: Merck Sharp & Dohme LLC

Inventor： Shaoyan Pan ,  Yiqiao Liu ,  Antong Chen ,  Gregory Goldmacher

IPC: G06V10/82 ,  G06V10/77 ,  G06V10/774

CPC classification number: G06V10/82 ,  G06V10/7715 ,  G06V10/7753 ,  G06V2201/03

Abstract: A system and method of multi-stage training of a transformer-based machine-learning model. The system performs at least two stages of the following three stages of training: During a first stage, the system pre-trains a transformer encoder via a first machine-learning network using an unlabeled 3D image dataset. During a second stage, the system fine-tunes the pre-trained transformer encoder via a second machine-learning network via a labeled 2D image dataset. During a third stage, the system further fine-tunes the previously pre-trained transformer encoder or fine-tuned transformer encoder via a third machine-learning network using a labeled 3D image dataset.

公开(公告)号：US11983943B2

公开(公告)日：2024-05-14

申请号：US17413971

申请日：2019-12-16

Applicant: UNIVERSITY OF PITTSBURGH-OF THE COMMONWEALTH SYSTEM OF HIGHER EDUCATION

Inventor： Srinivas C. Chennubhotla ,  Filippo Pullara ,  Douglass L. Taylor

IPC: G06V20/00 ,  G01N33/574 ,  G06T7/00 ,  G06V10/426 ,  G06V10/74 ,  G06V20/69

CPC classification number: G06V20/698 ,  G01N33/574 ,  G06T7/0012 ,  G06V10/426 ,  G06V10/761 ,  G06T2207/30024 ,  G06T2207/30096 ,  G06V2201/03

Abstract: A computational systems pathology spatial analysis platform includes: (i) a spatial heterogeneity quantification component configured for generating a global quantification of spatial heterogeneity among cells of varying phenotypes in multi-parameter cellular and subcellular imaging data; (ii) a microdomain identification component configured for identifying a plurality of microdomains for tissue samples based on the global quantification, each microdomain being associated with a tissue sample; and (iii) a weighted graph component configured for constructing a weighted graph for the multi-parameter cellular and subcellular imaging data, the weighted graph having a plurality of nodes and a plurality of edges each being located between a pair of the nodes, wherein in the weighted graph each node is a particular one of the microdomains and the edge between each pair of microdomains in the weighted graph is indicative of a degree of similarity between the pair of the microdomains.

公开(公告)号：US11983875B2

公开(公告)日：2024-05-14

申请号：US17606996

申请日：2020-04-30

Applicant: CAMBRIDGE ENTERPRISE LIMITED

Inventor： Adam Woolf ,  Martin Bennett

IPC: G06V10/764 ,  A61B5/00 ,  G06T7/00 ,  G06V10/40 ,  G06V10/766 ,  G06V10/774 ,  G06V10/82 ,  G16H30/20

CPC classification number: G06T7/0016 ,  A61B5/0066 ,  G06V10/40 ,  G06V10/764 ,  G06V10/766 ,  G06V10/774 ,  G06V10/82 ,  G16H30/20 ,  A61B2576/00 ,  G06T2207/10101 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30048 ,  G06T2207/30101 ,  G06T2207/30168 ,  G06V2201/03

Abstract: Embodiments of the present techniques provide apparatus and methods for analysing intracoronary images, for example to predict the likelihood of a disease, disease presentation or event, and/or to track performance of a drug or other treatment. The method may comprise: for each image in the set of images of a coronary artery: classifying the image, using a first neural network, for the presence or absence of diseased tissue; when the image is classified as having diseased tissue present, classifying the image, using a second neural network, for the presence or absence of an artefact; determining whether to analyse the image based on the classifying steps; when the image is to be analysed, analysing the image by identifying, using a third neural network, one or more features of interest in a coronary artery tissue; and measuring each identified feature of interest.

公开(公告)号：US20240153082A1

公开(公告)日：2024-05-09

申请号：US18471971

申请日：2023-09-21

Applicant: Versitech Limited ,  The Education University of Hong Kong

Inventor： Chengzhi Peng ,  Leung Ho Philip Yu ,  Wan Hang Keith Chiu ,  Xianhua Mao ,  Man Fung Yuen ,  Wai Kay Walter Seto

IPC: G06T7/00 ,  A61B6/00 ,  A61B6/03 ,  G06V10/764 ,  G06V10/82 ,  G06V20/50 ,  G16H30/40 ,  G16H50/20

CPC classification number: G06T7/0012 ,  A61B6/032 ,  A61B6/50 ,  G06V10/764 ,  G06V10/82 ,  G06V20/50 ,  G16H30/40 ,  G16H50/20 ,  G06T2200/24 ,  G06T2207/10081 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30056 ,  G06T2207/30096 ,  G06V2201/03

Abstract: Disclosed is a computer-implemented three-dimensional image classification system (CIS) for processing and/or analyzing non-contrast computed tomography (CT) medical imaging data. The CIS is a deep neural network containing multiple Convolutional Block Attention Module (CBAM) blocks, which contain convolutional layers for feature extraction followed by CBAMs. The CBAM applies channel attention to highlight more relevant features and spatial attention to focus on more important regions. Max pooling layers operably link adjacent pairs of CBAM blocks. The output of the final CBAM block is passed to two terminal fully connected layers to generate a diagnosis. This classification system can be used to perform efficient diagnosis of hepatocellular carcinoma using solely non-contrast CT images, with diagnostic performance comparable to that of a radiologist using the current LIRADS system.

公开(公告)号：US20240144708A1

公开(公告)日：2024-05-02

申请号：US18404746

申请日：2024-01-04

Applicant: DELTA ELECTRONICS, INC. ,  NATIONAL CHENG KUNG UNIVERSITY

Inventor： Chih-Yang CHEN ,  Pau-Choo CHUNG CHAN ,  Sheng-Hao TSENG

IPC: G06V30/142 ,  A61B5/00 ,  G06F18/2433 ,  G06T7/00 ,  G06T7/11 ,  G06V10/25 ,  G06V10/54 ,  G06V10/72 ,  G16H50/20

CPC classification number: G06V30/142 ,  A61B5/0013 ,  A61B5/0071 ,  A61B5/0088 ,  A61B5/7264 ,  G06F18/2433 ,  G06T7/0012 ,  G06T7/11 ,  G06V10/25 ,  G06V10/54 ,  G06V10/72 ,  G16H50/20 ,  A61B2576/02 ,  G06F2218/08 ,  G06F2218/12 ,  G06T2207/10064 ,  G06T2207/10152 ,  G06T2207/30036 ,  G06T2207/30088 ,  G06T2207/30096 ,  G06V2201/03 ,  G06V2201/07 ,  G06V2201/10

Abstract: An examination system is provided. The examination system includes an optical detector and analyzer. The optical detector emits a detection light source toward a target object and detects a respondent light which is induced from the target object in response to the detection light source to generate image data. The image data indicates a detection image. The analyzer receives the image data and determines which region of the target object the detection image belongs to according to the image data. When the analyzer determines that the detection image belongs to a specific region of the target object, the analyzer extracts at least one feature of the image data to serve as a basis for classification of the specific region.

公开(公告)号：US11972603B2

公开(公告)日：2024-04-30

申请号：US18130464

申请日：2023-04-04

Applicant: THYROSCOPE INC.

Inventor： Kyubo Shin

IPC: G06V10/776 ,  A61B3/14 ,  A61B5/00 ,  G06T7/00 ,  G06T7/33 ,  G06T7/73 ,  G06V40/18 ,  G16H30/40 ,  H04N7/18

CPC classification number: G06V10/776 ,  A61B3/14 ,  A61B5/4227 ,  G06T7/0014 ,  G06T7/73 ,  G06V40/193 ,  G16H30/40 ,  H04N7/183 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/30041 ,  G06V2201/03

Abstract: Provided is a diagnostic system including: a user terminal configured to take an image; and a server configured to obtain diagnosis assistance information on the basis of the image. The user terminal is configured to obtain a first photographing parameter, determine whether a pre-stored condition is satisfied, and transmit the first photographing parameter and a captured image to the server when it is determined that the pre-stored condition is satisfied. The server is configured to obtain a first verification parameter, determine whether to use the captured image as a diagnostic image which includes comparing the first verification parameter with the first photographing parameter, and obtain the diagnosis assistance information by using the diagnostic image when it is determined to use the captured image as the diagnostic image.