公开(公告)号：US12020436B2

公开(公告)日：2024-06-25

申请号：US17542535

申请日：2021-12-06

Applicant: City University of Hong Kong

Inventor： Yixuan Yuan ,  Xiaoqing Guo

IPC: G06T7/11 ,  G06N3/04 ,  G06V10/42 ,  G06V10/764 ,  G06V10/82 ,  G16H30/40

CPC classification number: G06T7/11 ,  G06N3/04 ,  G06V10/431 ,  G06V10/764 ,  G06V10/82 ,  G16H30/40 ,  G06T2207/10088 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30081 ,  G06V2201/03

Abstract: The present invention provides an unsupervised domain adaptive segmentation network comprises a feature extractor configured for extracting features from a 3D MRI scan image; a decorrelation and whitening module configured for preforming decorrelation and whitening transformation on the extracted features to obtain whitened features; a domain-specific feature translation module configured for translating domain-specific features from a source domain into a target domain for adapting the unsupervised domain adaptive network to the target domain; and a classifier configured for projecting the whitened features into a zonal segmentation prediction. By implementing the domain-specific feature translation module for transferring the knowledge learned from the labeled source domain data to unlabeled target domain data, domain gap between the source and target data can be narrowed. Therefore, the unsupervised domain adaptive segmentation network trained with labeled open-source prostate zonal segmentation dataset (source data) can perform in the target domain without performance degradation.

公开(公告)号：US12019674B2

公开(公告)日：2024-06-25

申请号：US16887036

申请日：2020-05-29

Applicant: NEW YORK UNIVERSITY

Inventor： Jing Wang ,  Prathamesh Kulkarni ,  Eric Robinson

IPC: A61K38/21 ,  G06F16/55 ,  G06F18/21 ,  G06F18/2321 ,  G06N3/04 ,  G06N3/08 ,  G06V10/762 ,  G06V10/764 ,  G06V20/69 ,  G16H30/20 ,  G16H30/40 ,  G16H50/20

CPC classification number: G06F16/55 ,  G06F18/2193 ,  G06F18/2321 ,  G06N3/04 ,  G06N3/08 ,  G06V10/763 ,  G06V10/764 ,  G06V20/693 ,  G06V20/698 ,  G16H30/20 ,  G16H30/40 ,  G16H50/20 ,  G06V2201/03

Abstract: A method of treating a subject comprises administering a treatment to a subject identified as having a high probability of distant metastatic recurrence, wherein the probability of distant metastatic recurrence was determined by a process, comprising acquiring at least one image of a tissue sample comprising a plurality of cells, taken from a subject, classifying each of the plurality of cells into categories, dividing the at least one image into a plurality of patches, calculating values for a plurality of morphological features based on the patches, and calculating a distant metastatic recurrence probability based on the values. A computer-implemented method of training a neural network and a system for characterizing a cancer in a subject are also described.

公开(公告)号：US20240203567A1

公开(公告)日：2024-06-20

申请号：US18555248

申请日：2022-04-12

Applicant: Kaliber Labs Inc.

Inventor： Mark RUIZ ,  Chandra JONELAGADDA ,  Ray RAHMAN ,  Aneesh JONELAGADDA

IPC: G16H30/40 ,  G06T3/40 ,  G06T5/20 ,  G06T7/20 ,  G06V10/44 ,  G06V10/54 ,  G06V10/74 ,  G06V20/70

CPC classification number: G16H30/40 ,  G06T3/40 ,  G06T5/20 ,  G06T7/20 ,  G06V10/44 ,  G06V10/54 ,  G06V10/761 ,  G06V20/70 ,  G06T2207/10068 ,  G06V2201/03

Abstract: Al-based systems and methods to annotate images and video from a surgical procedure may include extracting feature points (FP) from a still image (SI) of the procedure and each frame of a group of frames (GOF) from a procedure video and comparing FPs of the SI to FPs of each frame of the GOF to determine a match between the SI and a given frame from the video and a location in the video where the match occurred. Then the portion of the video containing the matched image is copied to create a video clip (VC) having a selected duration. Frames in the VC are analyzed to identify image features (IF), where a fidelity of IF identification is substantially unaffected when the IF is non-localizable or obscured. Then the SI and/or VC is annotated with information from the procedure, the information including or derived from the IFs.

公开(公告)号：US20240202927A1

公开(公告)日：2024-06-20

申请号：US18595213

申请日：2024-03-04

Applicant: Axial Medical Printing Limited

Inventor： Niall HASLAM ,  Lorenzo TROJAN ,  Daniel CRAWFORD

IPC: G06T7/11 ,  G06F18/24 ,  G06T7/00 ,  G06T17/20 ,  G06V10/26 ,  G16H30/40 ,  G16H50/50 ,  G16H50/70

CPC classification number: G06T7/11 ,  G06F18/24 ,  G06T7/0014 ,  G06T17/20 ,  G06V10/26 ,  G16H30/40 ,  G16H50/50 ,  G16H50/70 ,  G06T2200/08 ,  G06T2207/30004 ,  G06V2201/03

Abstract: There is provided a method for generating a 3D physical model of a patient specific anatomic feature from 2D medical images. The 2D medical images are uploaded by an end-user via a Web Application and sent to a server. The server processes the 2D medical images and automatically generates a 3D printable model of a patient specific anatomic feature from the 2D medical images using a segmentation technique. The 3D printable model is 3D printed as a 3D physical model such that it represents a 1:1 scale of the patient specific anatomic feature. The method includes the step of automatically identifying the patient specific anatomic feature.

公开(公告)号：US12014814B2

公开(公告)日：2024-06-18

申请号：US16775180

申请日：2020-01-28

Applicant: GE Precision Healthcare LLC

Inventor： Katelyn Nye ,  Gopal Avinash ,  Pal Tegzes ,  Gireesha Rao

IPC: G16H30/40 ,  G06F18/20 ,  G06F18/21 ,  G06F18/40 ,  G06N5/02 ,  G06N20/00 ,  G06T7/00 ,  G16H50/50

CPC classification number: G16H30/40 ,  G06F18/217 ,  G06F18/285 ,  G06F18/40 ,  G06N5/02 ,  G06N20/00 ,  G06T7/0012 ,  G16H50/50 ,  G06T2207/10116 ,  G06V2201/03

Abstract: Methods and systems are provided for tuning a static model with multiple operating points to adjust model performance without retraining the model or triggering a new regulatory clearance. In one embodiment, a method comprises, responsive to a request to tune a model, obtaining a tuning dataset including a set of medical images, executing the model using the set of medical images as input to generate model tuning output, and determining, for each operating point of a set of operating points, a set of tuning metric values based on the tuning dataset and the model tuning output relative to each operating point. An operating point from the set of operating points may be selected based on each set of tuning metric values and, upon a request to analyze a subsequent medical image, a representation of a finding output from the static model executed at the selected operating point.

公开(公告)号：US20240193902A1

公开(公告)日：2024-06-13

申请号：US18531782

申请日：2023-12-07

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Asateru KIMURA ,  Sho SASAKI ,  Kazumasa NORO ,  Yuka MATSUMURA

IPC: G06V10/22 ,  G06V10/26 ,  G06V10/44 ,  G06V10/762 ,  G06V10/764

CPC classification number: G06V10/23 ,  G06V10/267 ,  G06V10/457 ,  G06V10/763 ,  G06V10/764 ,  G06V2201/03

Abstract: A medical information processing device of an embodiment includes processing circuitry. The processing circuitry acquires a medical image to be processed, divides the medical image into a plurality of regions, calculates an image feature amount for each of the plurality of regions, generates a first cluster in which at least some of the plurality of regions are collected on the basis of the image feature amount, and identifies a sampling position on the basis of the first cluster.

公开(公告)号：US20240185627A1

公开(公告)日：2024-06-06

申请号：US18553290

申请日：2022-03-28

Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY ,  KOREA UNIVERSITY RESEARCH AND BUSINESS FOUNDATION

Inventor： Hongki YOO ,  Hyeong Soo NAM ,  Jin Won KIM ,  Sun Won KIM

IPC: G06V20/69 ,  G06T7/00

CPC classification number: G06V20/698 ,  G06T7/0012 ,  G06T2207/10064 ,  G06T2207/10101 ,  G06T2207/20084 ,  G06T2207/30101 ,  G06V2201/03

Abstract: An operation method of an analysis device operated by at least one processor includes: receiving a fusion image; and classifying tissue components in the fusion image using an artificial intelligence model. The fusion image includes first information obtained by imaging vascular tissue through an optical coherence tomography device, and second information obtained by imaging the vascular tissue through a fluorescence lifetime imaging device. The artificial intelligence model is a model trained to classify tissue components using structural features and fluorescence lifetime image information included in an input image.

公开(公告)号：US20240185626A1

公开(公告)日：2024-06-06

申请号：US18437612

申请日：2024-02-09

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

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

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

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：US20240177831A1

公开(公告)日：2024-05-30

申请号：US18524542

申请日：2023-11-30

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： Steffen RENISCH ,  Thomas NETSCH ,  Dirk SCHAEFER

IPC: G16H30/20 ,  G06V10/77 ,  G06V10/82 ,  H04N19/136 ,  H04N19/42

CPC classification number: G16H30/20 ,  G06V10/7715 ,  G06V10/82 ,  H04N19/136 ,  H04N19/42 ,  G06V2201/03

Abstract: The application describes various embodiments of a medical system, a computer program, and a method related to sequential transmission of compressed medical image data. As an example, a medical system comprising a local memory storing local machine executable instructions and a local computational system. Execution of the machine executable instructions further causes the computational system to: receive a feature vector descriptive of medical image data, wherein the feature vector is configured to be input into a decoder neural network, wherein the decoder neural network is configured to output an approximation of the medical image data when receiving at least a part of the feature vector as input, wherein the feature vector comprises a ranking assigning an importance to elements of the feature vector; and sequentially transmit portions of the feature vector to a remote computational system via a network connection, wherein the portions of the features vector with a higher importance are transmitted first.

公开(公告)号：US20240177504A1

公开(公告)日：2024-05-30

申请号：US18071943

申请日：2022-11-30

Applicant: SONY GROUP CORPORATION ,  Sony Corporation of America

Inventor： Haipeng Tang ,  Michael Zordan ,  Ming-Chang Liu

IPC: G06V20/69 ,  G06N3/0464 ,  G06V10/44 ,  G06V10/82 ,  G06V20/70

CPC classification number: G06V20/698 ,  G06N3/0464 ,  G06V10/44 ,  G06V10/82 ,  G06V20/695 ,  G06V20/70 ,  G06V2201/03

Abstract: The single cell identification described herein utilizes cell image information and extracts cell features with a neural network model to subtly distinguish the noise events from single cells, allowing the user to choose which different types of noise events to exclude depending on the requirement of applications. The fast neural network model is able to extract more abundant and specific cell features than handpicked features, which enables the model to be equipped with higher accuracy and higher discriminative capability of distinguishing noise events and identifying the single cells in real-time. Utilization of a neural network model for real-time single cell identification represents a novel technique never applied before. It allows high discriminative capability and high accuracy compared to traditional FACS (Fluorescence-activated Cell Sorting). The usefulness of this technique is to integrate with any brightfield (BF) model and fluorescence (FL) model to identify single cells for different downstream applications.